liu.seSearch for publications in DiVA
Change search
Link to record
Permanent link

Direct link
BETA
Merkel, Magnus
Publications (10 of 44) Show all publications
Eldén, L., Merkel, M., Ahrenberg, L. & Fagerlund, M. (2013). Computing Semantic Clusters by Semantic Mirroring and Spectral Graph Partitioning. Mathematics in Computer Science, 7, 293-313
Open this publication in new window or tab >>Computing Semantic Clusters by Semantic Mirroring and Spectral Graph Partitioning
2013 (English)In: Mathematics in Computer Science, ISSN 1661-8270, Vol. 7, p. 293-313Article in journal (Refereed) Published
Abstract [en]

Using the technique of semantic mirroring a graph is obtained that represents words and their translationsfrom a parallel corpus or a bilingual lexicon. The connectedness of the graph holds information about the semanticrelations of words that occur in the translations. Spectral graph theory is used to partition the graph, which leadsto a grouping of the words in different clusters. We illustrate the method using a small sample of seed words froma lexicon of Swedish and English adjectives and discuss its application to computational lexical semantics andlexicography.

Place, publisher, year, edition, pages
Basel: Springer, 2013
Keywords
Semantics · Cluster · Bilingual · Dictionary · Mirroring · WordNet · Graph · Spectral · Partitioning · Adjacency · Graph Laplacian · Fiedler vector · Matrix · Eigenvector · Eigenvalue
National Category
Computational Mathematics
Identifiers
urn:nbn:se:liu:diva-98175 (URN)10.1007/s11786-013-0159-4 (DOI)
Funder
Swedish Research Council
Available from: 2013-09-30 Created: 2013-09-30 Last updated: 2014-09-19
Merkel, M., Foo, J. & Ahrenberg, L. (2013). IPhraxtor - A linguistically informed system for extraction of term candidates. In: Stephan Oepen, Kristin Hagen, Janne Bondi Johannesse (Ed.), Proceedings of the 19th Nordic Conference on Computational Linguistics (Nodalida 2013), Oslo, May 22-24, 2013, NEALT Proceedings Series 16: . Paper presented at 19th Nordic Conference on Computational Linguistics (Nodalida 2013), Oslo, May 22-24, 2013 (pp. 121-132). Linköping: Linköping University Electronic Press, 85
Open this publication in new window or tab >>IPhraxtor - A linguistically informed system for extraction of term candidates
2013 (English)In: Proceedings of the 19th Nordic Conference on Computational Linguistics (Nodalida 2013), Oslo, May 22-24, 2013, NEALT Proceedings Series 16 / [ed] Stephan Oepen, Kristin Hagen, Janne Bondi Johannesse, Linköping: Linköping University Electronic Press, 2013, Vol. 85, p. 121-132Conference paper, Published paper (Refereed)
Abstract [en]

In this paper a method and a flexible tool for performing monolingual term extraction is presented; based on the use of syntactic analysis where information on parts-of-speech; syntactic functions and surface syntax tags can be utilised. The standard approaches to evaluating term extraction; namely by manual evaluation of the top n term candidates or by comparing to a gold standard consisting of a list of terms from a specific domain can have its advantages; but in this paper we try to realise a proposal by Bernier-Colborne (2012) where extracted terms are compared to a gold standard consisting of a test corpus where terms have been annotated in context. Apart from applying this evaluation to different configuratio

Place, publisher, year, edition, pages
Linköping: Linköping University Electronic Press, 2013
Series
Linköping Electronic Conference Proceedings, ISSN 1650-3686, E-ISSN 1650-3740 ; 85
Keywords
Computational terminology; term extraction; evaluation; terminological work
National Category
Engineering and Technology
Identifiers
urn:nbn:se:liu:diva-103994 (URN)978-91-7519-589-6 (ISBN)
Conference
19th Nordic Conference on Computational Linguistics (Nodalida 2013), Oslo, May 22-24, 2013
Available from: 2014-02-05 Created: 2014-02-05 Last updated: 2017-10-05Bibliographically approved
Holmqvist, M., Stymne, S., Ahrenberg, L. & Merkel, M. (2012). Alignment-based reordering for SMT. In: Proceedings of the Eight International Conference on Language Resources and Evaluation (LREC'12). Paper presented at The Eight International Conference on Language Resources and Evaluation (LREC'12), May 2012, Istanbul, Turkey (pp. 3436-3440).
Open this publication in new window or tab >>Alignment-based reordering for SMT
2012 (English)In: Proceedings of the Eight International Conference on Language Resources and Evaluation (LREC'12), 2012, p. 3436-3440Conference paper, Published paper (Other academic)
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.

Keywords
Mahine translation, statistical machine translation, word alignment, reordering
National Category
Language Technology (Computational Linguistics)
Identifiers
urn:nbn:se:liu:diva-80355 (URN)
Conference
The Eight International Conference on Language Resources and Evaluation (LREC'12), May 2012, Istanbul, Turkey
Available from: 2012-08-23 Created: 2012-08-23 Last updated: 2018-01-12
Merkel, M. & Gidlund, M. (2012). Integrerat termstöd för teknisk dokumentation. In: Anu Ylisalmi (Ed.), NORDTERM 17: Samarbetet ger resultat: från begreppskaos till överenskomna termer. Paper presented at NORDTERM 17, Vasa, Finland den 7–10 juni 2011 (pp. 149-153). Jyväskylä: Nordterm
Open this publication in new window or tab >>Integrerat termstöd för teknisk dokumentation
2012 (Swedish)In: NORDTERM 17: Samarbetet ger resultat: från begreppskaos till överenskomna termer / [ed] Anu Ylisalmi, Jyväskylä: Nordterm , 2012, p. 149-153Conference paper, Published paper (Other academic)
Place, publisher, year, edition, pages
Jyväskylä: Nordterm, 2012
Keywords
Skribentstöd, interaktivitet, kvalitetskontroll, skrivregler, terminologi
National Category
Specific Languages
Identifiers
urn:nbn:se:liu:diva-80289 (URN)978-952-9794-29-4 (ISBN)
Conference
NORDTERM 17, Vasa, Finland den 7–10 juni 2011
Projects
Multilingual term extraction and term structuring
Funder
Swedish Research Council
Available from: 2012-08-23 Created: 2012-08-23 Last updated: 2018-01-12
Merkel, M. & Nilsson, H. (2012). Term-O-Stat - ett fyrstegsprogram för terminologiarbete inom myndigheter. In: Anu Ylisalmi (Ed.), NORDTERM 17: Samarbetet ger resultat: från begreppskaos till överenskomna termer. Paper presented at NORDTERM 17, Vasa, Finland den 7–10 juni 2011 (pp. 222-228). Jyväskylä: Nordterm
Open this publication in new window or tab >>Term-O-Stat - ett fyrstegsprogram för terminologiarbete inom myndigheter
2012 (Swedish)In: NORDTERM 17: Samarbetet ger resultat: från begreppskaos till överenskomna termer / [ed] Anu Ylisalmi, Jyväskylä: Nordterm , 2012, p. 222-228Conference paper, Published paper (Other academic)
Place, publisher, year, edition, pages
Jyväskylä: Nordterm, 2012
Keywords
Terminologi, standardisering, process, språklagen
National Category
Specific Languages
Identifiers
urn:nbn:se:liu:diva-80288 (URN)078-952-9794-29-4 (ISBN)
Conference
NORDTERM 17, Vasa, Finland den 7–10 juni 2011
Projects
Multilingual term extraction and term structuring
Funder
Swedish Research Council
Available from: 2012-08-23 Created: 2012-08-23 Last updated: 2018-01-12
Merkel, M. & Nilsson, H. (2011). Getting to terms with terminology at Swedish public agencies. In: Tatiana Gornostay and Andrejs Vasiļjevs (Ed.), CHAT 2011: Creation, Harmonization and Application of Terminology Resources. Paper presented at CHAT 2011: Workshop on Creation, Harmonization and Application of Terminology Resources, May 11, Riga, Lettland (pp. 36-39). Tartu: Northern European Association for Language Technology (NEALT)
Open this publication in new window or tab >>Getting to terms with terminology at Swedish public agencies
2011 (English)In: CHAT 2011: Creation, Harmonization and Application of Terminology Resources / [ed] Tatiana Gornostay and Andrejs Vasiļjevs, Tartu: Northern European Association for Language Technology (NEALT) , 2011, p. 36-39Conference paper, Published paper (Refereed)
Abstract [en]

This paper describes on-going work aimed atassisting public agencies in Sweden to conformto the new Swedish Language Act(passed in 2009). The Language Act highlightsterminology as a key factor for a publicagency, as well as a responsibility for a publicagency to ensure that its terminology is madeavailable, used and developed. Term-O-Stat isan action program to help public agencies toimprove their terminological efforts. Term-OStatis divided into four distinct steps: 1) terminventory, 2) term classification, 3) conceptualanalysis and term choice, and 4) term implementation.We describe the four steps and alsoexperiences from the realization of step 1 and2 at the Swedish Social Insurance Agency.

Place, publisher, year, edition, pages
Tartu: Northern European Association for Language Technology (NEALT), 2011
Series
NEALT Proceedings Series, ISSN 1736-6305 ; 12
National Category
Specific Languages
Identifiers
urn:nbn:se:liu:diva-80328 (URN)
Conference
CHAT 2011: Workshop on Creation, Harmonization and Application of Terminology Resources, May 11, Riga, Lettland
Projects
Multilingual term extraction and term structuring
Funder
Swedish Research Council
Available from: 2012-08-23 Created: 2012-08-23 Last updated: 2018-01-12
Merkel, M. & Nilsson, H. (2011). Term-O-Stat - fyra steg för terminologiarbete på svenska myndigheter. Språkbruk, 4, 9-13
Open this publication in new window or tab >>Term-O-Stat - fyra steg för terminologiarbete på svenska myndigheter
2011 (Swedish)In: Språkbruk, ISSN 0358-9293, Vol. 4, p. 9-13Article in journal (Refereed) Published
Place, publisher, year, edition, pages
Helsingfors: Svenska avdelningen vid Forskningscentralen för de inhemska språken, 2011
Keywords
terminologi, språklagen, handlingsplan, termurval, termdefinition, verktygsintegration
National Category
Specific Languages
Identifiers
urn:nbn:se:liu:diva-80312 (URN)
Available from: 2012-08-23 Created: 2012-08-23 Last updated: 2018-01-12
Foo, J. & Merkel, M. (2010). Computer aided term bank creation and standardization: Building standardized term banks through automated term extraction and advanced editing tools. In: Marcel Thelen and Frieda Steurs (Ed.), Terminology in Everyday Life (pp. 163-180). John Benjamins Publishing Company
Open this publication in new window or tab >>Computer aided term bank creation and standardization: Building standardized term banks through automated term extraction and advanced editing tools
2010 (English)In: Terminology in Everyday Life / [ed] Marcel Thelen and Frieda Steurs, John Benjamins Publishing Company , 2010, p. 163-180Chapter in book (Other academic)
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.

 

Place, publisher, year, edition, pages
John Benjamins Publishing Company, 2010
Series
Terminology and Lexicography Research and Practice, ISSN 1388-8455 ; 13
Keywords
terminology, extraction, term bank, automation
National Category
Language Technology (Computational Linguistics) Computer Sciences
Identifiers
urn:nbn:se:liu:diva-59842 (URN)978 90 272 2337 1 (ISBN)
Available from: 2010-09-27 Created: 2010-09-27 Last updated: 2018-01-12Bibliographically approved
Fagerlund, M., Merkel, M., Eldén, L. & Ahrenberg, L. (2010). Computing Word Senses by Semantic Mirroring and Spectral Graph Partitioning. In: Carmen Banea, Alessandro Moschitti, Swapna Somasundaran and Fabio Massimo Zanzotto (Ed.), Proceedings of TextGraphs-5 - 2010 Workshop on Graph-based Methods for Natural Language Processing. Paper presented at 48th Annual Meeting of the Association for Computational Linguistics (pp. 103-107). Stroudsburg, PA, USA: The Association for Computational Linguistics
Open this publication in new window or tab >>Computing Word Senses by Semantic Mirroring and Spectral Graph Partitioning
2010 (English)In: Proceedings of TextGraphs-5 - 2010 Workshop on Graph-based Methods for Natural Language Processing / [ed] Carmen Banea, Alessandro Moschitti, Swapna Somasundaran and Fabio Massimo Zanzotto, Stroudsburg, PA, USA: The Association for Computational Linguistics , 2010, p. 103-107Conference paper, Published paper (Refereed)
Abstract [en]

Using the technique of ”semantic mirroring”a graph is obtained that representswords and their translations from a parallelcorpus or a bilingual lexicon. The connectednessof the graph holds informationabout the different meanings of words thatoccur in the translations. Spectral graphtheory is used to partition the graph, whichleads to a grouping of the words accordingto different senses. We also report resultsfrom an evaluation using a small sample ofseed words from a lexicon of Swedish andEnglish adjectives.

Place, publisher, year, edition, pages
Stroudsburg, PA, USA: The Association for Computational Linguistics, 2010
Keywords
lexical relations, sense relations, graph theory, spectral graph partitioning
National Category
Language Technology (Computational Linguistics) Computer Sciences Computational Mathematics
Identifiers
urn:nbn:se:liu:diva-59859 (URN)ISBN 978-1-932432-77-0 / 1-932432-77-9 (ISBN)
Conference
48th Annual Meeting of the Association for Computational Linguistics
Projects
Multilingual term extraction and term structuring
Available from: 2010-09-28 Created: 2010-09-28 Last updated: 2018-01-12
Merkel, M. & Nilsson, H. (2010). Tillgänglighet till terminologi: svenska myndigheters ansvar. In: Språkteknologi för ökad tillgänglighet: . Paper presented at Rapport från ett nordiskt seminarium Linköping, 27–28 oktober 2010 (pp. 35-47). Linköping: Linköping University Electronic Press
Open this publication in new window or tab >>Tillgänglighet till terminologi: svenska myndigheters ansvar
2010 (Swedish)In: Språkteknologi för ökad tillgänglighet, Linköping: Linköping University Electronic Press, 2010, p. 35-47Conference paper, Published paper (Other academic)
Abstract [sv]

Med språklagen (SFS 2009:600), som antogs i juli 2009, har terminologi blivit allt viktigare för myndigheter eftersom de enligt paragraf 12 i lagen har ett särskilt ansvar för att terminologi finns tillgänglig, men också för att den används och utvecklas. Terminologicentrum TNC och Fodina Language Technology presenterar här sitt arbete med att få igång ett fungerande erminologiarbete på myndigheter enligt språklagen med hjälp av Term-O-Stat, ett fyrstegsprogram med inslag av både maskinell terminologihantering och automatisk termextraktion samt mer traditionellt terminologiarbete. Terminologiarbete i förhållande till annat språkarbete inom myndigheter, särskilt klarspråksarbete, beskrivs också.

Place, publisher, year, edition, pages
Linköping: Linköping University Electronic Press, 2010
Series
Linköping Electronic Conference Proceedings, ISSN 1650-3686, E-ISSN 1650-3740 ; 54
Keywords
terminologi, standardisering, process, tillgänglighet
National Category
Specific Languages
Identifiers
urn:nbn:se:liu:diva-80304 (URN)978-91-7393-095-6 (ISBN)
Conference
Rapport från ett nordiskt seminarium Linköping, 27–28 oktober 2010
Available from: 2012-08-23 Created: 2012-08-23 Last updated: 2018-01-31Bibliographically approved
Organisations

Search in DiVA

Show all publications