liu.seSearch for publications in DiVA
Endre søk
Begrens søket
12345 51 - 100 of 206
RefereraExporteraLink til resultatlisten
Permanent link
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Treff pr side
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sortering
  • Standard (Relevans)
  • Forfatter A-Ø
  • Forfatter Ø-A
  • Tittel A-Ø
  • Tittel Ø-A
  • Type publikasjon A-Ø
  • Type publikasjon Ø-A
  • Eldste først
  • Nyeste først
  • Skapad (Eldste først)
  • Skapad (Nyeste først)
  • Senast uppdaterad (Eldste først)
  • Senast uppdaterad (Nyeste først)
  • Disputationsdatum (tidligste først)
  • Disputationsdatum (siste først)
  • Standard (Relevans)
  • Forfatter A-Ø
  • Forfatter Ø-A
  • Tittel A-Ø
  • Tittel Ø-A
  • Type publikasjon A-Ø
  • Type publikasjon Ø-A
  • Eldste først
  • Nyeste først
  • Skapad (Eldste først)
  • Skapad (Nyeste først)
  • Senast uppdaterad (Eldste først)
  • Senast uppdaterad (Nyeste først)
  • Disputationsdatum (tidligste først)
  • Disputationsdatum (siste først)
Merk
Maxantalet träffar du kan exportera från sökgränssnittet är 250. Vid större uttag använd dig av utsökningar.
  • 51.
    Flycht-Eriksson, Annika
    et al.
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Jönsson, Arne
    Linköpings universitet, Institutionen för datavetenskap. Linköpings universitet, Tekniska högskolan.
    A Spoken Dialogue System Utilizing Spatial Information1998Inngår i: Proceedings of ICSLP'98,Sydney, Australia, 1998Konferansepaper (Fagfellevurdert)
  • 52.
    Flycht-Eriksson (Silvervarg), Annika
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    A Survey of Knowledge Sources in Dialogue Systems1999Inngår i: Electronic Transactions on Artificial Intelligence, ISSN 1403-3534, Vol. 3, nr 2, s. 5-32Artikkel i tidsskrift (Annet vitenskapelig)
    Abstract [en]

    Dialogue systems utilise a variety of knowledge sources and models. However, there is a confusion concerning the purposes and contributions of specific models and the relationships among them. In this paper we present a study of different dialogue systems and the knowledge sources and models they use. The models are characterised in terms of what knowledge they contain and the roles of various models and the relations between them are discussed. Implications for development of dialogue systems are also presented.

  • 53.
    Flycht-Eriksson (Silvervarg), Annika
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Design and use of ontologies in information-providing dialogue systems2004Doktoravhandling, monografi (Annet vitenskapelig)
    Abstract [en]

    In this thesis, the design and use of ontologies as domain knowledge sources in information-providing dialogue systems are investigated. The research is divided into two parts, theoretical investigations that have resulted in a requirements specifications on the design of ontologies to be used in information-providing dialogue systems, and empirical work on the development of a framework for use of ontologies in information-providing dialogue systems.

    The framework includes three models: A model for ontology-based semantic analysis of questions. A model for ontology-based dialogue management, specifically focus management and clarifications. A model for ontology-based domain knowledge management, specifically transformation of user requests to system oriented concepts used for information retrieval.

    In this thesis, it is shown that using ontologies to represent and reason on domain knowledge in dialogue systems has several advantages. A deeper semantic analysis is possible in several modules and a more natural and efficient dialogue can be achieved. Another important aspect is that it facilitates portability; to be able to reuse adapt the dialogue system to new tasks and domains, since the domain-specific knowledge is separated form generic features in the dialogue system architecture. Other advantages are that it reduces the complexity of linguistic produced in various domains.

  • 54.
    Flycht-Eriksson (Silvervarg), Annika
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Design of Ontologies for Dialogue Interaction and Information Extraction2003Inngår i: Proceedings of IJCAI'03 workshop on Knowledge and reasoning in practical dialogue systems, Acapulco, Mexico', 2003Konferansepaper (Fagfellevurdert)
  • 55.
    Flycht-Eriksson (Silvervarg), Annika
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Domain Knowledge Management in Information-providing Dialogue Systems2001Licentiatavhandling, monografi (Annet vitenskapelig)
    Abstract [en]

    In this thesis a new concept called domain knowledge management for informationproviding dialogue systems is introduced. Domain knowledge management includes issues related to representation and use of domain knowledge as well as access of background information sources, issues that previously have been incorporated in dialogue management.

    The work on domain knowledge management reported in this thesis can be divided in two parts. On a general theoretical level, knowledge sources and models used for dialogue management, including domain knowledge management, are studied and related to the capabilities they support. On a more practical level, domain knowledge management is examined in the contexts of a dialogue system framework and a specific instance of this framework, the ÖTRAF system. In this system domain knowledge management is implemented in a separate module, a Domain Knowledge Manager.

    The use of a specialised Domain Knowledge Manager has a number of advantages. The first is that dialogue management becomes more focused as it only has to consider dialogue phenomena, while domain-specific reasoning is handled by the Domain Knowledge Manager. Secondly, porting of a system to new domains is facilitated since domain-related issues are separated out in specialised domain knowledge sources. The third advantage with a separate module for domain knowledge management is that domain knowledge sources can be easily modified, exchanged, and reused.

  • 56.
    Flycht-Eriksson (Silvervarg), Annika
    et al.
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Jönsson, Arne
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Some empirical findings on dialogue management and domain ontologies in dialogue systems - Implications from an evaluation of BirdQuest2003Inngår i: 4th Annual SIGdial Workshop on Discourse and Dialogue,Sapporo, 2003, 2003Konferansepaper (Fagfellevurdert)
  • 57.
    Flycht-Eriksson (Silvervarg), Annika
    et al.
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Jönsson, Arne
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Merkel, Magnus
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Sundblad, Håkan
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Ontology-driven Information-providing Dialogue Systems2003Inngår i: Proceedings of the Americas Conference on Information Systems / [ed] Dennis Galletta and Jeanne Ross, Association for Information Systems , 2003Konferansepaper (Fagfellevurdert)
  • 58.
    Foo, Jody
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Computational Terminology: Exploring Bilingual and Monolingual Term Extraction2012Licentiatavhandling, med artikler (Annet vitenskapelig)
    Abstract [en]

    Terminologies are becoming more important to modern day society as technology and science continue to grow at an accelerating rate in a globalized environment. Agreeing upon which terms should be used to represent which concepts and how those terms should be translated into different languages is important if we wish to be able to communicate with as little confusion and misunderstandings as possible.

    Since the 1990s, an increasing amount of terminology research has been devoted to facilitating and augmenting terminology-related tasks by using computers and computational methods. One focus for this research is Automatic Term Extraction (ATE).

    In this compilation thesis, studies on both bilingual and monolingual ATE are presented. First, two publications reporting on how bilingual ATE using the align-extract approach can be used to extract patent terms. The result in this case was 181,000 manually validated English-Swedish patent terms which were to be used in a machine translation system for patent documents. A critical component of the method used is the Q-value metric, presented in the third paper, which can be used to rank extracted term candidates (TC) in an order that correlates with TC precision. The use of Machine Learning (ML) in monolingual ATE is the topic of the two final contributions. The first ML-related publication shows that rule induction based ML can be used to generate linguistic term selection patterns, and in the second ML-related publication, contrastive n-gram language models are used in conjunction with SVM ML to improve the precision of term candidates selected using linguistic patterns.

    Delarbeid
    1. Computer aided term bank creation and standardization: Building standardized term banks through automated term extraction and advanced editing tools
    Åpne denne publikasjonen i ny fane eller vindu >>Computer aided term bank creation and standardization: Building standardized term banks through automated term extraction and advanced editing tools
    2010 (engelsk)Inngår i: Terminology in Everyday Life / [ed] Marcel Thelen and Frieda Steurs, John Benjamins Publishing Company , 2010, s. 163-180Kapittel i bok, del av antologi (Annet vitenskapelig)
    Abstract [en]

    Using a standardized term bank in both authoring and translation processes can facilitate the use of consistent terminology, which in turn minimizes confusion and frustration from the readers. One of the problems of creating a standardized term bank, is the time and effort required. Recent developments in term extraction techniques based on word alignment can improve extraction of term candidates when parallel texts are available. The aligned units are processed automatically, but a large quantity of term candidates will still have to be processed by a terminologist to select which candidates should be promoted to standardized terms. To minimize the work needed to process the extracted term candidates, we propose a method based on using efficient editing tools, as well as ranking the extracted set of term candidates by quality. This sorted set of term candidates can then be edited, categorized and filtered in a more effective way. In this paper, the process and methods used to arrive at a standardized term bank are presented and discussed.

     

    sted, utgiver, år, opplag, sider
    John Benjamins Publishing Company, 2010
    Serie
    Terminology and Lexicography Research and Practice, ISSN 1388-8455 ; 13
    Emneord
    terminology, extraction, term bank, automation
    HSV kategori
    Identifikatorer
    urn:nbn:se:liu:diva-59842 (URN)978 90 272 2337 1 (ISBN)
    Tilgjengelig fra: 2010-09-27 Laget: 2010-09-27 Sist oppdatert: 2018-01-12bibliografisk kontrollert
    2. Automatic Extraction and Manual Validation of Hierarchical Patent Terminology
    Åpne denne publikasjonen i ny fane eller vindu >>Automatic Extraction and Manual Validation of Hierarchical Patent Terminology
    Vise andre…
    2009 (engelsk)Inngår i: NORDTERM 16. Ontologier og taksonomier.: Rapport fra NORDTERM 2009 / [ed] B. Nistrup Madsen & H. Erdman Thomsen, Copenhagen, Denmark: Copenhagen Business School Press, 2009, s. 249-262Konferansepaper, Publicerat paper (Fagfellevurdert)
    Abstract [en]

    Several methods can be applied to create a set of validated terms from existing documents. In this paper we describe an automatic bilingual term candidate extraction method, and the validation process used to create a hierarchical patent terminology. The process described was used to extract terms from patent texts, commissioned by the Swedish Patent Office with the purpose of using the terms for machine translation. Information on the correct linguistic inflection patterns and hierarchical partitioning of terms based on their use are of utmost importance.The process contains six phases, 1) Analysis of the source material and system configuration; 2) Term candidate extraction; 3) Term candidate filtering and initial linguistic validation; 4) Manual validation by domain experts; 5) Final linguistic validation; and 6) Publishing the validated terms.Input to the extraction process consisted of more than 91 000 patent document pairs in English and Swedish, 565 million words in English and 450 million words in Swedish. The English documents were supplied in EBD SGML format and the Swedish documents were supplied in OCR processed scans of patent documents. After grammatical and statistical analysis, the documents were word-aligned. Using the word-aligned material, candidate terms were extracted based on linguistic patterns. 750 000 term candidates were extracted and stored in a relational database. The term candidates were processed in 8 months resulting in 181 000 unique validated term pairs that were exported into several hierarchically organized OLIF files.

    sted, utgiver, år, opplag, sider
    Copenhagen, Denmark: Copenhagen Business School Press, 2009
    Emneord
    automatic term extraction, computational terminology, patent terminology
    HSV kategori
    Identifikatorer
    urn:nbn:se:liu:diva-75236 (URN)978-87-994577-0-0 (ISBN)
    Konferanse
    NORDTERM 2009, København, Danmark 9‐12. juni 2009
    Tilgjengelig fra: 2012-02-23 Laget: 2012-02-22 Sist oppdatert: 2018-01-12bibliografisk kontrollert
    3. Terminology extraction and term ranking for standardizing term banks
    Åpne denne publikasjonen i ny fane eller vindu >>Terminology extraction and term ranking for standardizing term banks
    2007 (engelsk)Inngår i: Proceedings of 16th Nordic Conference of Computational Linguistics Nodalida,2007 / [ed] Joakim Nivre, Heiki-Jaan Kaalep, Kadri Muischnek and Mare Koit, Tartu, Estonia: University of Tartu , 2007, s. 349-354Konferansepaper, Publicerat paper (Fagfellevurdert)
    Abstract [en]

    This paper presents how word alignment techniques could be used for building standardized term banks. It is shown that time and effort could be saved by a relatively simple evaluation metric based on frequency data from term pairs, and source and target distributions inside the alignment results. The proposed Q-value metric is shown to outperform other tested metrics such as Dice's coefficient, and simple pair frequency.

     

    sted, utgiver, år, opplag, sider
    Tartu, Estonia: University of Tartu, 2007
    Emneord
    terminology extraction, metric, word alignment
    HSV kategori
    Identifikatorer
    urn:nbn:se:liu:diva-41011 (URN)54924 (Lokal ID)978-9985-4-0513-0 (ISBN)54924 (Arkivnummer)54924 (OAI)
    Konferanse
    NODALIDA 2007, 16th Nordic Conference of Computational Linguistics, 24-26 May 2007, University of Tartu, Estonia
    Tilgjengelig fra: 2010-09-29 Laget: 2009-10-10 Sist oppdatert: 2018-01-13bibliografisk kontrollert
    4. Using machine learning to perform automatic term recognition
    Åpne denne publikasjonen i ny fane eller vindu >>Using machine learning to perform automatic term recognition
    2010 (engelsk)Inngår i: Proceedings of the LREC 2010 Workshop on Methods for automatic acquisition of Language Resources and their evaluation methods / [ed] Núria Bel, Béatrice Daille, Andrejs Vasiljevs, European Language Resources Association, 2010, s. 49-54Konferansepaper, Publicerat paper (Fagfellevurdert)
    Abstract [en]

    In this paper a machine learning approach is applied to Automatic Term Recognition (ATR). Similar approaches have been successfully used in Automatic Keyword Extraction (AKE). Using a dataset consisting of Swedish patent texts and validated terms belonging to these texts, unigrams and bigrams are extracted and annotated with linguistic and statistical feature values. Experiments using a varying ratio between positive and negative examples in the training data are conducted using the annotated n-grams. The results indicate that a machine learning approach is viable for ATR. Furthermore, a machine learning approach for bilingual ATR is discussed. Preliminary analysis however indicate that some modifications have to be made to apply the monolingual machine learning approach to a bilingual context.

    sted, utgiver, år, opplag, sider
    European Language Resources Association, 2010
    HSV kategori
    Identifikatorer
    urn:nbn:se:liu:diva-75237 (URN)000356879501100 ()978-2-9517408-6-0 (ISBN)
    Konferanse
    LREC 2010 Workshop on Methods for automatic acquisition of Language Resources and their evaluation methods, 23 May 2010, Valletta, Malta
    Tilgjengelig fra: 2012-03-01 Laget: 2012-02-22 Sist oppdatert: 2018-01-12bibliografisk kontrollert
    5. Exploring termhood using language models
    Åpne denne publikasjonen i ny fane eller vindu >>Exploring termhood using language models
    2011 (engelsk)Inngår i: Proceedings of the Workshop CHAT 2011: Creation, Harmonization and Application of Terminology Resources / [ed] Tatiana Gornostay, Andrejs Vasiljevs, Tartu University Library (Estonia): Northern European Association for Language Technology (NEALT) , 2011, s. 32-35Konferansepaper, Publicerat paper (Fagfellevurdert)
    Abstract [en]

    Term extraction metrics are mostly based on frequency counts. This can be a problem when trying to extract previously unseen multi-word terms. This paper explores whether smoothed language models can be used instead. Although a simplistic use of language models is examined in this paper, the results indicate that with more refinement, smoothed language models may be used instead of unsmoothed frequency-count based termhood metrics.

    sted, utgiver, år, opplag, sider
    Tartu University Library (Estonia): Northern European Association for Language Technology (NEALT), 2011
    Serie
    NEALT Proceedings Series, ISSN 1736-8197, E-ISSN 1736-6305 ; Vol. 12
    Emneord
    automatic term extraction, computational terminology, machine learning
    HSV kategori
    Identifikatorer
    urn:nbn:se:liu:diva-75238 (URN)
    Konferanse
    NODALIDA 2011 Workshop Creation, Harmonization and Application of Terminology Resources, May 11, 2011, Riga, Latvia
    Tilgjengelig fra: 2012-02-23 Laget: 2012-02-22 Sist oppdatert: 2018-01-12bibliografisk kontrollert
  • 59.
    Foo, Jody
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Exploring termhood using language models2011Inngår i: Proceedings of the Workshop CHAT 2011: Creation, Harmonization and Application of Terminology Resources / [ed] Tatiana Gornostay, Andrejs Vasiljevs, Tartu University Library (Estonia): Northern European Association for Language Technology (NEALT) , 2011, s. 32-35Konferansepaper (Fagfellevurdert)
    Abstract [en]

    Term extraction metrics are mostly based on frequency counts. This can be a problem when trying to extract previously unseen multi-word terms. This paper explores whether smoothed language models can be used instead. Although a simplistic use of language models is examined in this paper, the results indicate that with more refinement, smoothed language models may be used instead of unsmoothed frequency-count based termhood metrics.

  • 60.
    Foo, Jody
    et al.
    Linköpings universitet, Tekniska högskolan. Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk.
    Merkel, Magnus
    Linköpings universitet, Tekniska högskolan. Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk.
    Building Standardized Term Bases Through Automated Term Extraction and Advanced Editing Tools2006Inngår i: International Conference on Terminology,2006, Antwerp: ICT , 2006Konferansepaper (Fagfellevurdert)
  • 61.
    Foo, Jody
    et al.
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Merkel, Magnus
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Computer aided term bank creation and standardization: Building standardized term banks through automated term extraction and advanced editing tools2010Inngår i: Terminology in Everyday Life / [ed] Marcel Thelen and Frieda Steurs, John Benjamins Publishing Company , 2010, s. 163-180Kapittel i bok, del av antologi (Annet vitenskapelig)
    Abstract [en]

    Using a standardized term bank in both authoring and translation processes can facilitate the use of consistent terminology, which in turn minimizes confusion and frustration from the readers. One of the problems of creating a standardized term bank, is the time and effort required. Recent developments in term extraction techniques based on word alignment can improve extraction of term candidates when parallel texts are available. The aligned units are processed automatically, but a large quantity of term candidates will still have to be processed by a terminologist to select which candidates should be promoted to standardized terms. To minimize the work needed to process the extracted term candidates, we propose a method based on using efficient editing tools, as well as ranking the extracted set of term candidates by quality. This sorted set of term candidates can then be edited, categorized and filtered in a more effective way. In this paper, the process and methods used to arrive at a standardized term bank are presented and discussed.

     

  • 62.
    Foo, Jody
    et al.
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Merkel, Magnus
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Using machine learning to perform automatic term recognition2010Inngår i: Proceedings of the LREC 2010 Workshop on Methods for automatic acquisition of Language Resources and their evaluation methods / [ed] Núria Bel, Béatrice Daille, Andrejs Vasiljevs, European Language Resources Association, 2010, s. 49-54Konferansepaper (Fagfellevurdert)
    Abstract [en]

    In this paper a machine learning approach is applied to Automatic Term Recognition (ATR). Similar approaches have been successfully used in Automatic Keyword Extraction (AKE). Using a dataset consisting of Swedish patent texts and validated terms belonging to these texts, unigrams and bigrams are extracted and annotated with linguistic and statistical feature values. Experiments using a varying ratio between positive and negative examples in the training data are conducted using the annotated n-grams. The results indicate that a machine learning approach is viable for ATR. Furthermore, a machine learning approach for bilingual ATR is discussed. Preliminary analysis however indicate that some modifications have to be made to apply the monolingual machine learning approach to a bilingual context.

  • 63.
    Gorrell, Genevieve
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Generalized Hebbian Algorithm for Dimensionality Reduction in Natural Language Processing2006Doktoravhandling, monografi (Annet vitenskapelig)
    Abstract [en]

    The current surge of interest in search and comparison tasks in natural language processing has brought with it a focus on vector space approaches and vector space dimensionality reduction techniques. Presenting data as points in hyperspace provides opportunities to use a variety of welldeveloped tools pertinent to this representation. Dimensionality reduction allows data to be compressed and generalised. Eigen decomposition and related algorithms are one category of approaches to dimensionality reduction, providing a principled way to reduce data dimensionality that has time and again shown itself capable of enabling access to powerful generalisations in the data. Issues with the approach, however, include computational complexity and limitations on the size of dataset that can reasonably be processed in this way. Large datasets are a persistent feature of natural language processing tasks. This thesis focuses on two main questions. Firstly, in what ways can eigen decomposition and related techniques be extended to larger datasets? Secondly, this having been achieved, of what value is the resulting approach to information retrieval and to statistical language modelling at the ngram level? The applicability of eigen decomposition is shown to be extendable through the use of an extant algorithm; the Generalized Hebbian Algorithm (GHA), and the novel extension of this algorithm to paired data; the Asymmetric Generalized Hebbian Algorithm (AGHA). Several original extensions to the these algorithms are also presented, improving their applicability in various domains. The applicability of GHA to Latent Semantic Analysisstyle tasks is investigated. Finally, AGHA is used to investigate the value of singular value decomposition, an eigen decomposition variant, to ngram language modelling. A sizeable perplexity reduction is demonstrated.

  • 64.
    Gorrell, Genevieve
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Language Modelling and Error Handling in Spoken Dialogue Systems2004Licentiatavhandling, monografi (Annet vitenskapelig)
    Abstract [en]

    Language modelling for speech recognition is an area of research currently divided between two main approaches: stochastic and grammar-based approaches are each being differently preferred for their respective strengths and weaknesses. At the same time, dialogue systems researchers are becoming aware of the potential value of handling recognition failures better to improve the user experience. This work aims to bring together these two areas of interest, in investigating how language modelling approaches can be used to improve the way in which speech recognition errors are handled.

    Three practical ways of combining approaches to language modelling in spoken dialogue systems are presented. Firstly, it is demonstrated that a stochastic language model-based recogniser can be used to detect out-of-vocabulary material in a grammar-based system with high precision. Ways in which the technique could be used are discussed. Then, two approaches to providing users with recognition failure assistance are described. In the first, poor recognition results are re-recognised with a stochastic language model, and a decision tree classitier is then used to select a context-specific help message. The approach thereby improves on traditional approaches, where only general help is provided on recognition failure. A user study shows that the approach is well-received. The second differs from the first in its use of layered recognisers and a modified dialogue, and uses Latent Semantic Analysis for the classification part of the task. Decision-tree classification outperforms Latent Semantic Analysis in the work presented here, though it is suggested that there is the potential to improve LSA performance such that it may ultimately prove superior.

  • 65.
    Gorrell, Genevieve
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Recognition Error Handling in Spoken Dialogue Systems2003Inngår i: Proceedings of 2nd International Conference on Mobile andUbiquitous Multimedia 2003., 2003Konferansepaper (Fagfellevurdert)
  • 66.
    Gorrell, Genevieve
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Using Statistical Language Modelling to Identify NewVocabulary in a Grammar-Based Speech Recognition System2003Inngår i: Proceedings ofEurospeech 2003, 2003, s. 2729-2732Konferansepaper (Fagfellevurdert)
  • 67.
    Gorrell, Genevieve
    et al.
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Lewin, Ian
    Netdecisions Technology Centre, Cambridge.
    Rayner, Manny
    Netdecisions Technology Centre, Cambridge.
    Adding Intelligent Help to Mixed Initiative Spoken Dialogue Systems2002Inngår i: Proceedings of ICSLP 2002, 2002Konferansepaper (Fagfellevurdert)
  • 68.
    Gorrell, Genevieve
    et al.
    Linköpings universitet, Tekniska högskolan. Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk.
    Webb, B
    Generalized Hebbian Algorithm for Latent Semantic Analysis2005Inngår i: Interspeech,2005, Lisbon: Casual Productions , 2005, s. 1325-Konferansepaper (Fagfellevurdert)
  • 69.
    Granlund, Helena
    et al.
    Santa Anna IT Research Institute, Linköping, Sweden.
    Granlund, Rego
    Santa Anna IT Research Institute, Linköping, Sweden.
    Dahlbäck, Nils
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Institutionen för datavetenskap, Interaktiva och kognitiva system. Linköpings universitet, Filosofiska fakulteten.
    The Effect of a GPS on Learning with regards to Performance and Communication in Municipal Crisis Response2011Inngår i: Universal Access in Human-Computer Interaction. Applications and Services, Part IV / [ed] Stephanidis, Constantine, Springer Berlin/Heidelberg, 2011, s. 215-224Konferansepaper (Fagfellevurdert)
    Abstract [en]

    This paper describes the basic learning aspects of crises management training in a computer simulated environment. A total of 108 professionals, 18 teams, contributed to the study where the impact of a GPS on C2 work was investigated. A comparison between professional groups on performance and learning show that the GPS has an impact that differed depending on the teams professional composition.

  • 70.
    Granlund, Rego
    et al.
    Linköpings universitet, Institutionen för datavetenskap. Linköpings universitet, Tekniska högskolan.
    Granlund, Helena
    Linköpings universitet, Institutionen för datavetenskap. Linköpings universitet, Tekniska högskolan.
    Dahlbäck, Nils
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Institutionen för datavetenskap, Interaktiva och kognitiva system. Linköpings universitet, Filosofiska fakulteten.
    Johansson, Björn
    Swedish Defence Research Agency.
    The Effect of a Geographical Information System on Communication in Professional Emergency Response Organizations2010Inngår i: ISCRAM 2010, 7th International Conference on Information Systems for Crisis Response and Management, ISCRAM , 2010Konferansepaper (Fagfellevurdert)
    Abstract [en]

    This paper describes the basic communication analysis performed in a research project with an ambition to investigate the impact of geographical information system (GIS) on crisis management organizations. The goal is to compare the communication between command and control teams that have access to a GIS with geographical position information (GPS) capability in its command post with teams that only have access to paper maps. The method used is controlled experiments using the C3Fire micro-world. A total of 108 professionals, forming 18 teams, participated in the study. The participating professionals were members of Swedish municipal crisis management organizations. The result shows that the communication pattern connected to giving orders have a different distribution depending on if the teams used GIS or paper maps. The result also shows that the communication volume is reduced if the teams use GIS.

  • 71.
    Gulz, Agneta
    et al.
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Haake, Magnus
    Lunds universitet.
    Challenging Gender Stereotypes using Virtual Pedagogical Characters2010Inngår i: Gender Issues in Learning and Working with Information Technology: Social Constructs and Cultural Contexts, / [ed] Sara Goodman, Shirlsy Booth & Gill Kirkup, IGI Global , 2010Kapittel i bok, del av antologi (Annet vitenskapelig)
    Abstract [en]

    This paper explores motivational and cognitive effects of more neutral or androgynous-looking versus more feminine-looking and masculine-looking virtual characters. A user study is presented, in which 158 students, aged 17-19, encountered four virtual characters that were visually manipulated to represent gender stereotypicality versus androgyny. On the one hand we explored students’ attitudes towards the different characters as seen in how they ranked them as preferred presenters and articulated their arguments for doing so. On the other hand we looked for patterns as to which character(s) influenced female and male students most positively with respect to their attitude towards a university level computer engineering programme. Results from the study are presented and discussed. We conclude by pointing towards future research and potential within the area.

     

  • 72.
    Gulz, Agneta
    et al.
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Haake, Magnus
    Lunds universitet.
    Virtuella rollmodeller och androgynitetens potential2009Inngår i: Individen, tekniken och lärande / [ed] Jonas Linderoth. Roger Säljö, & Ulf P.Lundgren, Carlssons förlag , 2009Kapittel i bok, del av antologi (Annet (populærvitenskap, debatt, mm))
    Abstract [sv]

    Virtuella karaktärer, det vill säga mer eller mindre människoliknande och interaktiva datorgenererade figurer, har sedan länge förekommit i datorspel. På senare år har de även blivit allt vanligare i digitala lärmiljöer. De uppträder där i form av virtuella instruktörer, coacher, rollspelskaraktärer, lärkompanjoner och avatarer (alter egos) i pedagogiskt material från förskola till högskola likväl som i specialistutbildningar. I bredare pedagogiska sammanhang träffar man på dem i egenskap av till exempel virtuella rådgivare och informatörer.

    Skälen till att använda virtuella pedagogiska karaktärer kan variera och i Gulz (2004) ges en översikt samt kritisk diskussion av olika möjliga pedagogiska vinster. Veletsianos

    Scharber och Doering (2008) fördjupar den kritiska diskussionen i en artikel med titeln ”När sex, droger och våld kommer in i klassrummet: Konversation mellan ungdomar och en kvinnlig pedagogisk agent”. Den analys de presenterar av loggade konversationer visar en kraftig diskrepans mellan pedagogisk intention, å ena sidan, och vardaglig praktik där elever interagerar med virtuella pedagogiska karaktärer, å andra sidan. Former av interaktion, kommunikation och språkbruk, som normalt är otillåtna och förekom sparsamt i de aktuella klassrummen, gjorde här ett inträde på bred front.

    I denna text kommer vi emellertid att titta närmare på pedagogiska möjligheter. Specifikt fokuserar vi på följande fråga: ”Kan virtuella pedagogiska karaktärer vara ett redskap för att erbjuda alternativa kulturella bilder inom områden med starka genusassociationer som till exempel ingenjörsutbildning och datorteknik?”.

    Innan vi går in på huvudtemat inleder vi med att presentera en begreppslig och temamässig bakgrund till den kommande analysen och diskussionen kring kulturella bilder, rollmodeller och genusproblematik.

     

  • 73.
    Gulz, Agneta
    et al.
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan. Lund University.
    Haake, Magnus
    Designvetenskap, Lund Univeristy.
    Silvervarg, Annika
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Sjödén, Björn
    Lund Uniiversity.
    Veletsianos, George
    Instructional design, University of Austin, USA.
    Building a Social Conversational Pedagogical Agent: Design Challenges and Methodological approaches2011Inngår i: Conversational Agents and Natural Language Interaction: Techniques and Effective Practices / [ed] Diana Perez-Marin and Ismael Pascual-Nieto, IGI Global, 2011, s. 128-155Kapittel i bok, del av antologi (Annet vitenskapelig)
    Abstract [en]

    This chapter discusses design challenges encountered when developing a conversational pedagogical agent. By tracing the historical roots of pedagogical agents in Intelligent Tutoring Systems (ITS), we discern central developments in creating an agent that is both knowledgeable and fosters a social relationship with the learner. Main challenges faced when attempting to develop a pedagogical agent of this kind relate to: i) learners’ expectations on the agent’s knowledge and social profile, ii) dealing with learners’ engagement in off-task conversation and iii) managing potential abuse of the agent. We discuss these challenges and possible ways to address them, with reference to an ongoing Research & Development project, and with a focus on the design of a pedagogical agent’s visual embodiment and its conversational capabilities.

  • 74.
    Gulz, Agneta
    et al.
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Mellström, Ulf
    Luleå Tekniska universitet.
    Gränsöverskridande IT-roller2009Inngår i: IT och lärande / [ed] Maria Folke-Fichtelius, Carlsson Bokförlag, 2009, s. 153-168Kapittel i bok, del av antologi (Annet (populærvitenskap, debatt, mm))
    Abstract [sv]

    Vilken bild ser du framför dig om du tänker på en typisk datoringenjör? Svaret på den frågan blir sannolikt olika beroende på i vilket land och i vilken del av världen som frågan ställs. I till exempel Holland är den kulturella bilden av en dataingenjör så starkt förknippad med en asocial och asexuell datornörd att det utgör ett starkt hinder för ungdomar, särskilt unga kvinnor, att välja en sådan yrkesbana. Även om bilden inte är lika stark i Sverige är datoringenjör inte heller något drömyrke för svenska ungdomar att utbilda sig till. Andelen kvinnor som går system- och datatekniska utbildningar på de tekniska högskolorna ligger också väsentligt lägre än andelen män.

    Men i flera länder i Sydostasien är bilden en helt annan. Här betraktas datoringenjör som ett statusfyllt framtidsyrke, och en stor andel av dem som utbildar sig och arbetar inom IT-relaterade yrken är kvinnor. Hur kommer det sig att det är så stora skillnader mellan olika länder och världsdelar inom IT- området? Hur har dessa bilder och mönster uppstått? Det är några av de frågor som ett av forskningsprojekten inom LearnIT har intresserat sig för. Ett annat projekt har i sin tur riktat fokus mot hur IT i sig kan användas som redskap för att förändra de genusmönster inom IT-området som framträder i västvärlden

  • 75.
    Gulz, Agneta
    et al.
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Silvervarg Flycht-Eriksson, Annika
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Sjödén, Björn
    LUCS, Lunds universitet.
    Design for off-task interaction – rethinking pedagogy in technology enhanced learning2010Inngår i: ICALT 2010 10th IEEE International Conference on Advanced Learning Technologies, Institute of Electrical and Electronics Engineers (IEEE), 2010, s. 204-206Konferansepaper (Fagfellevurdert)
    Abstract [en]

    In this paper, we argue for the design of off-task interaction in technology enchanced learning. This implies a rethinking of pedagogy which can substantially contribute to achieving specific learning goals. We describe a work-in-progress and provide concrete examples of how we deal with relevant issues raised by allowing for off-task interactions in an educational math game as an integrated learning system.

  • 76.
    Gustafson, Joakim
    et al.
    KTH.
    Elmberg, Patrik
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Carlson, Rolf
    KTH.
    Jönsson, Arne
    Linköpings universitet, Institutionen för datavetenskap. Linköpings universitet, Tekniska högskolan.
    An educational dialogue system with a user controllable dialogue manager1998Inngår i: Proceedings of ICSLP'98, Sydney, Australia, 1998Konferansepaper (Fagfellevurdert)
  • 77.
    Haake, Magnus
    et al.
    Lunds universitet.
    Gulz, Agneta
    Linköpings universitet, Tekniska högskolan. Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk.
    A Look at the Roles of Look & Roles in Embodied Pedagogical Agents – a User Preference Perspective2009Inngår i: International Journal of Artificial Intelligence in Education, ISSN 1560-4292, Vol. 19(1)Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    The paper presents a theoretical framework addressing three aspects of embodied pedagogical agents: visual static appearance, pedagogical role, and communicative style. The framework is then applied to a user study where 90 school children (age 12‑15) in a dummy multimedia program were presented with either an instructor or a learning companion condition. They were then to choose between eight visually different embodied pedagogical agents: four more naturalistic (detailed & 3D-rendered) and four more stylized (simplified & cartoonish). Finally the participants were to choose between a strictly task-oriented versus a task- and relation-oriented pedagogical agent.

    The goal of the study was to explore possible relations between the three aspects mentioned above with respect to user preferences. Results were: (i) When the agent was introduced as a learning companion, female students displayed a significant tendency to choose a more stylized visual character, (ii) When the agent was introduced as a learning companion, female students displayed a significant tendency to choose a task- and relation-oriented agent, (iii) In the case when students had chosen a more stylized character, there was a significant tendency to choose a task- and relational-oriented agent.

    The paper also discusses limitations and strengths of the study, and advocates careful descriptions in studies of this kind – especially regarding the notion of visual realism.

     

  • 78.
    Haake, Magnus
    et al.
    Lund University, Sweden .
    Silvervarg, Annika
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Tärning, Betty
    Cognitive Science, Lund University, Sweden.
    Gulz, Agneta
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Teaching Her, Him…or Hir? Challenges for a Cross-Cultural Study2011Inngår i: Intelligent Virtual Agents: 10th International Conference, IVA 2011, Reykjavik, Iceland, September 15-17, 2011. Proceedings / [ed] Stephan Kopp, Stacy Marsella, K Thorisson, Hannes Vilhjalmsson, Springer Berlin/Heidelberg, 2011, s. 447-448Kapittel i bok, del av antologi (Fagfellevurdert)
    Abstract [en]

    The paper discusses some cultural considerations that we stand before in developing and exploiting an agent based educational software for use by Swedish and American students, age 11-14. The reported cultural challenges arise in software develop­ment, study designs, and decisions on actual pedagogical use in the two cultural settings.

  • 79.
    Hassling, Linda
    et al.
    Inst medicinsk teknik Linköpings universitet.
    Babic, Ankica
    Linköpings universitet, Tekniska högskolan. Linköpings universitet, Institutionen för medicinsk teknik, Medicinsk informatik.
    Jönsson, Arne
    Linköpings universitet, Tekniska högskolan. Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk.
    Lönn, Urban
    Dept Cardio-Thoracic surgery Uppsala universitet.
    Ahn, Henrik Casimir
    Linköpings universitet, Hälsouniversitetet. Linköpings universitet, Institutionen för medicin och vård, Thoraxkirurgi. Östergötlands Läns Landsting, Hjärtcentrum, Thorax-kärlkliniken.
    Assessing patient information needs as a part of man-machine dialogue development2001Inngår i: AMIA2001,2001, Washington: Hanley&Belfus , 2001, s. 922-Konferansepaper (Fagfellevurdert)
  • 80.
    Herdagdelen, Amac
    et al.
    University of Trento, Rovereto, Italy.
    Ciaramita, Massimiliano
    Google, Zürich, Switzerland.
    Mahler, Daniel
    Google, Zürich, Switzerland.
    Holmqvist, Maria
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Hall, Keith
    Google, Zurich, Sweden .
    Riezler, Stefan
    Google, Zürich, Switzerland.
    Alfonseca, Enrique
    Google, Zürich, Switzerland.
    Generalized syntactic and semantic models of query reformulation2010Inngår i: SIGIR '10 Proceedings of the 33rd international ACM SIGIR conference on Research and development in information retrieval, ACM Press, 2010, s. 283-290Konferansepaper (Annet vitenskapelig)
    Abstract [en]

    We present a novel approach to query reformulation which combines syntactic and semantic information by means of generalized Levenshtein distance algorithms where the substitution operation costs are based on probabilistic term rewrite functions. We investigate unsupervised, compact and efficient models, and provide empirical evidence of their effectiveness. We further explore a generative model of query reformulation and supervised combination methods providing improved performance at variable computational costs. Among other desirable properties, our similarity measures incorporate information-theoretic interpretations of taxonomic relations such as specification and generalization.

  • 81.
    Holmqvist, Maria
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Heuristic Word Alignment with Parallel Phrases2010Inngår i: Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10) / [ed] Nicoletta Calzolari (Conference Chair) and Khalid Choukri and Bente Maegaard and Joseph Mariani and Jan Odijk and Stelios Piperidis and Mike Rosner and Daniel Tapias, European Language Resources Association (ELRA) , 2010Konferansepaper (Fagfellevurdert)
  • 82.
    Holmqvist, Maria
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Memory-based learning of word translation2007Inngår i: Proceedings of 16th Nordic Conference of Computational Linguistics Nodalida,2007 / [ed] oakim Nivre, Heiki-Jaan Kaalep, Kadri Muischnek, Mare Koit, Tartu: University of Tartu , 2007, s. 231-234Konferansepaper (Fagfellevurdert)
    Abstract [en]

    A basic task in machine translation is to choose the right translation for source words with several possible translations in the target language. In this paper we treat word translation as a word sense disambiguation problem and train memory-based classifiers on words with alternative translations. The training data was automatically labeled with the corresponding translations by word-aligning a parallel corpus. Results show that many words were translated with accuracy above the baseline.

  • 83.
    Holmqvist, Maria
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Word Alignment by Re-using Parallel Phrases2008Licentiatavhandling, monografi (Annet vitenskapelig)
    Abstract [en]

    In this thesis we present the idea of using parallel phrases for word alignment. Each parallel phrase is extracted from a set of manual word alignments and contains a number of source and target words and their corresponding alignments. If a parallel phrase matches a new sentence pair, its word alignments can be applied to the new sentence. There are several advantages of using phrases for word alignment. First, longer text segments include more  context and will be more likely to produce correct word alignments than shorter segments or single words. More importantly, the use of longer phrases makesit possible to generalize words in the phrase by replacing words by parts-of-speech or other grammatical information. In this way, the number of words covered by the extracted phrases can go beyond the words and phrases that were present in the original set of manually aligned sentences. We present  experiments with phrase-based word alignment on three types of English–Swedish parallel corpora: a software manual, a novel and proceedings of the European Parliament. In order to find a balance between improved coverage and high alignment accuracy we investigated different properties of generalised phrases to identify which types of phrases are likely to produce accurate alignments on new data. Finally, we have compared phrase-based word alignments to state-of-the-art statistical alignment with encouraging results. We show that phrase-based word alignments can be used to enhance statistical word alignment. To evaluate word alignments an English–Swedish reference set for the Europarl corpus was constructed. The guidelines for producing this reference alignment are presented in the thesis.

  • 84.
    Holmqvist, Maria
    et al.
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Ahrenberg, Lars
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    A Gold Standard for English-Swedish Word Alignment2011Inngår i: Proceedings of the 18th Nordic Conference of Computational Linguistics NODALIDA 2011 / [ed] Bolette Sandford Pedersen, Gunta Nepore and Inguna Skadina, Tartu, Estland, 2011, s. 106-113Konferansepaper (Annet vitenskapelig)
    Abstract [en]

    Word alignment gold standards are an importantresource for developing and evaluatingword alignment methods. In thispaper we present a free English–Swedishword alignment gold standard consistingof texts from Europarl with manually verifiedword alignments. The gold standardcontains two sets of word aligned sentences,a test set for the purpose of evaluationand a training set that can be usedfor supervised training. The guidelinesused for English–Swedish alignment werecreated based on guidelines for other languagepairs and with statistical machinetranslation as the targeted application. Wealso present results of intrinsic evaluationusing our gold standard and discuss the relationshipto extrinsic evaluation in a statisticalmachine translation system.

  • 85.
    Holmqvist, Maria
    et al.
    Linköpings universitet, Tekniska högskolan. Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk.
    Ahrenberg, Lars
    Linköpings universitet, Tekniska högskolan. Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk.
    Stymne, Sara
    Linköpings universitet, Tekniska högskolan. Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk.
    High-precision Word Alignment with Parallel Phrases2008Inngår i: The second Swedish Language Technology Conference SLTC-08,2008, 2008, s. 45-46Konferansepaper (Fagfellevurdert)
  • 86.
    Holmqvist, Maria
    et al.
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Stymne, Sara
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Ahrenberg, Lars
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Experiments with word alignment, normalization and clause reordering for SMT between English and German2011Inngår i: Proceedings of the Sixth Workshop on Statistical Machine Translation (WMT 2011) / [ed] Chris Callison-Burch, Philipp Koehn, Christof Monz, Omar F. Zaidan, 2011, s. 393-398Konferansepaper (Fagfellevurdert)
    Abstract [en]

    This paper presents the LIU system for the WMT 2011 shared task for translation between German and English. For English– German we attempted to improve the translation tables with a combination of standard statistical word alignments and phrase-based word alignments. For German–English translation we tried to make the German text more similar to the English text by normalizing German morphology and performing rule-based clause reordering of the German text. This resulted in small improvements for both translation directions.

  • 87.
    Holmqvist, Maria
    et al.
    Linköpings universitet, Tekniska högskolan. Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk.
    Stymne, Sara
    Linköpings universitet, Tekniska högskolan. Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk.
    Ahrenberg, Lars
    Linköpings universitet, Tekniska högskolan. Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk.
    Getting to Know Moses: Initial Experiments on German-English Factored Translation2007Inngår i: Proceedings of the Second Workshop on Statistical Machine Translation,2007, Stroudsberg, PA: Association for Computational Linguistics , 2007, s. 181-Konferansepaper (Fagfellevurdert)
  • 88.
    Holmqvist, Maria
    et al.
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Stymne, Sara
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Ahrenberg, Lars
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Merkel, Magnus
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Alignment-based reordering for SMT2012Inngår i: Proceedings of the Eight International Conference on Language Resources and Evaluation (LREC'12), 2012, s. 3436-3440Konferansepaper (Annet vitenskapelig)
    Abstract [en]

    We present a method for improving word alignment quality for phrase-based statistical machine translation by reordering the source text according to the target word order suggested by an initial word alignment. The reordered text is used to create a second word alignment which can be an improvement of the first alignment, since the word order is more similar. The method requires no other pre-processing such as part-of-speech tagging or parsing. We report improved Bleu scores for English-to-German and English-to-Swedish translation. We also examined the effect on word alignment quality and found that the reordering method increased recall while lowering precision, which partly can explain the improved Bleu scores. A manual evaluation of the translation output was also performed to understand what effect our reordering method has on the translation system. We found that where the system employing reordering differed from the baseline in terms of having more words, or a different word order, this generally led to an improvement in translation quality.

  • 89.
    Holmqvist, Maria
    et al.
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Stymne, Sara
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Jody, Foo
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Ahrenberg, Lars
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Improving alignment for SMT by reordering and augmenting the training corpus2009Inngår i: Proceedings of the Fourth Workshop on Statistical Machine Translation (WMT09), Athens, Greece, 2009, s. 120-124Konferansepaper (Fagfellevurdert)
    Abstract [en]

    We describe the LIU systems for English-German and German-English translation in the WMT09 shared task. We focus on two methods to improve the word alignment: (i) by applying Giza++ in a second phase to a reordered training corpus, where reordering is based on the alignments from the first phase, and (ii) by adding lexical data obtained as high-precision alignments from a different word aligner. These methods were studied in the context of a system that uses compound processing, a morphological sequence model for German, and a part-of-speech sequence model for English. Both methods gave some improvements to translation quality as measured by Bleu and Meteor scores, though not consistently. All systems used both out-of-domain and in-domain data as the mixed corpus had better scores in the baseline configuration.

  • 90.
    Ibrahim, Aseel
    et al.
    Linköpings universitet, Institutionen för datavetenskap, ASLAB - Application Systems Laboratory. Linköpings universitet, Tekniska högskolan.
    Johansson, Pontus
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Multimodal Dialogue Systems: A Case Study for Interactive TV2002Inngår i: Proceedings of the 7thERCIM Workshop on User Interfaces for All. Paris, France. 2002, 2002Konferansepaper (Fagfellevurdert)
  • 91.
    Ibrahim (Berglund), Aseel
    et al.
    Linköpings universitet, Institutionen för datavetenskap, ASLAB - Application Systems Laboratory. Linköpings universitet, Tekniska högskolan.
    Johansson, Pontus
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Multimodal Dialogue Systems for Interactive TV Applications2002Inngår i: Proceedings of the 4th IEEE International Conference on Multimodal Interfaces 2002 (ICMI’02), Pittsburgh, USA, 2002, s. 117-122Konferansepaper (Fagfellevurdert)
  • 92.
    Johansson, Pontus
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    MadFilm - a Multimodal Approach to Handle Search and Organization in a Movie Recommendaton System2003Inngår i: Proceedings of the 1st Nordic Symposium on Multimodal Communication. Helsingör, Denmark, September 25-26, 2003, 2003, s. 53-65Konferansepaper (Fagfellevurdert)
  • 93.
    Johansson, Pontus
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Natural Language Interaction in Personalized EPGs2003Inngår i: Proceedings of the 3rd Workshop on Personalization in TV (9th International Conference on User Modeling). Johnstown (PA), USA, June 23, 2003, 2003, s. 27-31Konferansepaper (Fagfellevurdert)
  • 94.
    Johansson, Pontus
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    User Modeling in Dialogue Systems2002Rapport (Annet vitenskapelig)
  • 95.
    Johansson, Pontus
    et al.
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Filosofiska fakulteten.
    Degerstedt, Lars
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Filosofiska fakulteten.
    Jönsson, Arne
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Iterative Development of an Information-Providing Dialogue System2002Inngår i: Proceedings of the 7th ERCIM Workshop "User Interfaces for All" Paris, France, 2002., 2002Konferansepaper (Fagfellevurdert)
  • 96.
    Johansson, Pontus
    et al.
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Degerstedt, Lars
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Jönsson, Arne
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Iterative Developmentof an Information-Providing Dialogue System2002Inngår i: Proceedings of the 7th ERCIM Workshop on User Interfaces for All. Paris, France. 2002., 2002, s. 29-36Konferansepaper (Fagfellevurdert)
  • 97.
    Jonsson, Håkan
    et al.
    Voice Provider Sweden AB.
    Eklund, Robert
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Tekniska högskolan.
    Gender differences in verbal behaviour in a call routing speech application2011Inngår i: Proceedings from Fonetik 2011, Quarterly Progress and Status Report TMH-QPSR, Volume 51, 2011, Stockholm: Universitetsservice , 2011, s. 81-84Konferansepaper (Annet vitenskapelig)
    Abstract [en]

    This paper reports results on verbal behavior in a live natural language call routing speechapplication. Differences between male and female callers in terms of verbosity are investigated, andput in relation to three variations of the system prompts. Findings show that in this particularapplication female callers are more verbose than male callers for open style prompts, while there isno difference for a directed style prompt.

  • 98.
    Jonsson, Ing-Marie
    et al.
    Linköpings universitet, Institutionen för datavetenskap, Interaktiva och kognitiva system. Linköpings universitet, Filosofiska fakulteten.
    Dahlbäck, Nils
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Institutionen för datavetenskap, Interaktiva och kognitiva system. Linköpings universitet, Filosofiska fakulteten.
    I Can’t Hear You? Driver’s Interacting with Male or Female Voices in Native or Non-Native Language2011Inngår i: Universal Access in Human-Computer Interaction. Context Diversity, Part III, Springer Berlin/Heidelberg, 2011, s. 298-305Konferansepaper (Fagfellevurdert)
    Abstract [en]

    Many vehicles today are equipped with navigation systems, and all of these systems use speech or a combination of speech and graphics to provide drivers with directions to their destinations. This study investigates the effect of gender of voice when providing driving instructions in English to drivers that are non-native speakers of English. In a 2(native/non-native) by 2(gender of voice) between participant study, 40 participants in age group 18-25 drove in a driving simulator for 25 minutes with navigation information system that gave drivers directions to a set destination. Results show that gender of voice did not affect native English speaking drivers. For non-native speakers, however, a female voice worked better for both female and male drivers. Non-native speakers consistently missed to act on navigational information give by the male voice. Design implications for voice systems are discussed.

  • 99.
    Jonsson, Ing-Marie
    et al.
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Filosofiska fakulteten. Linköpings universitet, Institutionen för datavetenskap, Interaktiva och kognitiva system.
    Dahlbäck, Nils
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Institutionen för datavetenskap, Interaktiva och kognitiva system. Linköpings universitet, Filosofiska fakulteten.
    Impact of Voice Variation in Speech-Based In-Vehicle Systems on Attitude and Driving Behavior2009Inngår i: Human Factors and Ergonomics Society Europe Chapter (HFES), 2009Konferansepaper (Fagfellevurdert)
    Abstract [en]

    Automobile manufacturers are making information systems available in all vehicles. Mostsystems are screen based, but increasingly systems are either hybrids (screen/speech) orspeech based. Speech systems in vehicles may have advantages over screen based in-vehiclesystems; literature suggests that speech can be less distracting than screen-based interactions.Nonetheless, using speech systems in the car also introduces social and attitudinal effects.Voices are not neutral! Voices carry socio-economic cues including indicators of gender, age,personality, emotional state, ethniticity, education and social status. Perception ofinformation presented by the voice is influenced by the perception of the voice demographics.This is further complicated by different individuals perceiving voices in different ways. A voicethat is seen as positive by one individual can be perceived negatively by another. We presentresults from a number of driving simulator studies of speech based in-vehicle systems. These studiesshow that speech based in-vehicle systems can affect drivers’ attitude and drivingperformance. Attitude and performance can be improved, but the effect of the voice can also proveharmful for driving behaviour and driving safety. This makes it important to include the voice as adesign parameter of speech-based in-vehicle systems.

  • 100.
    Jönsson, Arne
    Linköpings universitet, Institutionen för datavetenskap, NLPLAB - Laboratoriet för databehandling av naturligt språk. Linköpings universitet, Hälsouniversitetet.
    A Dialogue Manager for Natural Language Interfaces1995Inngår i: Proceedings of the Pacific Association for Computational Linguistics, Second conference The University of Queensland, Brisbane, Australia, 1995Konferansepaper (Fagfellevurdert)
12345 51 - 100 of 206
RefereraExporteraLink til resultatlisten
Permanent link
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf