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

Direct link
BETA
Tan, He
Publications (10 of 38) Show all publications
Tan, H., Kaliyaperumal, R. & Benis, N. (2012). Ontology-Driven Construction of Domain Corpus with Frame Semantics Annotations. In: Computational linguistics and intelligent text processing: . Paper presented at 13th Annual Conference on Intelligent Text Processing and Computational Linguistics, CICLing 2012; New Delhi; India (pp. 54-65). Springer Berlin/Heidelberg
Open this publication in new window or tab >>Ontology-Driven Construction of Domain Corpus with Frame Semantics Annotations
2012 (English)In: Computational linguistics and intelligent text processing, Springer Berlin/Heidelberg, 2012, p. 54-65Conference paper, Published paper (Refereed)
Abstract [en]

Semantic Role Labeling plays a key role in many text mining applications. The development of SRL systems for the biomedical domain is frustrated by the lack of large domain specific corpora that are labeled with semantic roles. In this paper we proposed a method for building corpus that are labeled with semantic roles for the domain of biomedicine. The method is based on the theory of frame semantics, and uses domain knowledge provided by ontologies. By using the method, we have built a corpus for transport events strictly following the domain knowledge provided by GO biological process ontology. We compared one of our frames to a BioFrameNet frame. We also examined the gaps between the semantic classification of the target words in this domain-specific corpus and in FrameNet and PropBank/VerbNet data. The successful corpus construction demonstrates that ontologies, as a formal representation of domain knowledge, can instruct us and ease all the tasks in building this kind of corpus. Furthermore, ontological domain knowledge leads to well-defined semantics exposed on the corpus, which will be very valuable in text mining applications.

Place, publisher, year, edition, pages
Springer Berlin/Heidelberg, 2012
Series
Lecture Notes in Computer Science, ISSN 0302-9743, E-ISSN 1611-3349 ; 7181
National Category
Computer Sciences
Identifiers
urn:nbn:se:liu:diva-74807 (URN)10.1007/978-3-642-28604-9_5 (DOI)978-3-642-28603-2 (ISBN)978-3-642-28604-9 (ISBN)
Conference
13th Annual Conference on Intelligent Text Processing and Computational Linguistics, CICLing 2012; New Delhi; India
Available from: 2012-02-09 Created: 2012-02-09 Last updated: 2018-01-26
Tan, H., Kaliyaperumal, R. & Benis, N. (2011). Building frame-based corpus on the basis of ontological domain knowledge. In: Proceedings of the Workshop on BioNLP: . Paper presented at BioNLP (pp. 74-82). Association for Computational Linguistics
Open this publication in new window or tab >>Building frame-based corpus on the basis of ontological domain knowledge
2011 (English)In: Proceedings of the Workshop on BioNLP, Association for Computational Linguistics, 2011, p. 74-82Conference paper, Published paper (Refereed)
Abstract [en]

Semantic Role Labeling (SRL) plays a key role in many NLP applications. The development of SRL systems for the biomedical domain is frustrated by the lack of large domain-specific corpora that are labeled with semantic roles. Corpus development has been very expensive and time-consuming. In this paper we propose a method for building frame-based corpus on the basis of domain knowledge provided by ontologies. We believe that ontologies, as a structured and semantic representation of domain knowledge, can instruct and ease the tasks in building the corpora. In the paper we present a corpus built by using the method. We compared it to BioFrameNet, and examined the gaps between the semantic classification of the target words in the domain-specific corpus and in FrameNet and Prop-Bank/VerbNet.

Place, publisher, year, edition, pages
Association for Computational Linguistics, 2011
National Category
Computer Sciences
Identifiers
urn:nbn:se:liu:diva-74810 (URN)978-1-932432-91-6 (ISBN)
Conference
BioNLP
Available from: 2012-02-09 Created: 2012-02-09 Last updated: 2018-01-12
Tan, H., Kaliyaperumal, R. & Benis, N. (2011). Ontology-driven Construction of Corpus with Frame Semantics Annotations. In: poster at The Fourth International Symposium on Languages in Biology and Medicine: . Paper presented at The Fourth International Symposium on Languages in Biology and Medicine.
Open this publication in new window or tab >>Ontology-driven Construction of Corpus with Frame Semantics Annotations
2011 (English)In: poster at The Fourth International Symposium on Languages in Biology and Medicine, 2011Conference paper, Published paper (Refereed)
National Category
Computer Sciences
Identifiers
urn:nbn:se:liu:diva-74811 (URN)
Conference
The Fourth International Symposium on Languages in Biology and Medicine
Available from: 2012-02-09 Created: 2012-02-09 Last updated: 2018-01-12
Tan, H. (2010). A study on the relation between linguistics-oriented and domain-specific semantics. In: Proceedings of the 3rd International Workshop on Semantic Web Applications and Tools for the Life Sciences: . Paper presented at 3rd International Workshop on Semantic Web Applications and Tools for the Life Sciences.
Open this publication in new window or tab >>A study on the relation between linguistics-oriented and domain-specific semantics
2010 (English)In: Proceedings of the 3rd International Workshop on Semantic Web Applications and Tools for the Life Sciences, 2010Conference paper, Published paper (Refereed)
Abstract [en]

In this paper we dealt with the comparison and linking between lexical resources with domain knowledge provided by ontologies. It is one of the issues for the combination of the Semantic Web Ontologies and Text Mining. We investigated the relations between the linguisticsoriented and domain-specific semantics, by associating the GO biological process concepts to the FrameNet semantic frames. The result shows the gaps between the linguistics-oriented and domain-specific semantics on the classification of events and the grouping of target words. The result provides valuable information for the improvement of domain ontologies supporting for text mining systems. And also, it will result in benefits to language understanding technology.

Series
CEUR Workshop Proceedings, ISSN 1613-0073 ; 698
National Category
Computer Sciences
Identifiers
urn:nbn:se:liu:diva-74809 (URN)
Conference
3rd International Workshop on Semantic Web Applications and Tools for the Life Sciences
Available from: 2012-02-09 Created: 2012-02-09 Last updated: 2018-01-12
Lambrix, P., Liu, Q. & Tan, H. (2009). A system for repairing missing is-a structure in ontologies. In: Semantic Web Applications and Tools for Life Sciences: . Paper presented at Semantic Web Applications and Tools for Life Sciences.
Open this publication in new window or tab >>A system for repairing missing is-a structure in ontologies
2009 (English)In: Semantic Web Applications and Tools for Life Sciences, 2009Conference paper, Published paper (Refereed)
Series
CEUR Workshop Proceedings, ISSN 1613-0073 ; 559
National Category
Engineering and Technology
Identifiers
urn:nbn:se:liu:diva-51523 (URN)
Conference
Semantic Web Applications and Tools for Life Sciences
Available from: 2009-11-05 Created: 2009-11-05 Last updated: 2015-04-30
Lambrix, P., Liu, Q. & Tan, H. (2009). Aligning anatomy ontologies in the Ontology Alignment Evaluation Initiative. In: 25th Workshop of the Swedish Artificial Intelligence Society: . Paper presented at 25th Workshop of the Swedish Artificial Intelligence Society (pp. 13-20).
Open this publication in new window or tab >>Aligning anatomy ontologies in the Ontology Alignment Evaluation Initiative
2009 (English)In: 25th Workshop of the Swedish Artificial Intelligence Society, 2009, p. 13-20Conference paper, Published paper (Refereed)
Series
Linköping Electronic Conference Proceedings, ISSN 1650-3686, E-ISSN 1650-3740 ; 35
National Category
Engineering and Technology
Identifiers
urn:nbn:se:liu:diva-28214 (URN)
Conference
25th Workshop of the Swedish Artificial Intelligence Society
Available from: 2009-10-09 Created: 2009-10-09 Last updated: 2018-02-07
Lambrix, P., Strömbäck, L. & Tan, H. (2009). Information integration in bioinformatics with ontologies and standards (1ed.). In: Semantic Techniques for the Web: The REWERSE perspective (pp. 343-376). Springer Berlin/Heidelberg
Open this publication in new window or tab >>Information integration in bioinformatics with ontologies and standards
2009 (English)In: Semantic Techniques for the Web: The REWERSE perspective, Springer Berlin/Heidelberg, 2009, 1, p. 343-376Chapter in book (Refereed)
Abstract [en]

New experimental methods allow researchers within molecular and systems biology to rapidly generate larger and larger amounts of data. This data is often made publicly available on the Internet and although this data is extremely useful, we are not using its full capacity. One important reason is that we still lack good ways to connect or integrate information from different resources. One kind of resource is the over 1000 data sources freely available on the Web. As most data sources are developed and maintained independently, they are highly heterogeneous. Information is also updated frequently. Other kinds of resources that are not so well-known or commonly used yet are the ontologies and the standards. Ontologies aim to define a common terminology for a domain of interest. Standards provide a way to exchange data between data sources and tools, even if the internal representations of the data in the resources and tools are different. In this chapter we argue that ontological knowledge and standards should be used for integration of data. We describe properties of the different types of data sources, ontological knowledge and standards that are available on the Web and discuss how this knowledge can be used to support integrated access to multiple biological data sources. Further, we present an integration approach that combines the identified ontological knowledge and standards with traditional information integration techniques. Current integration approaches only cover parts of the suggested approach. We also discuss the components in the model on which much recent work has been done in more detail: ontology-based data source integration, ontology alignment and integration using standards. Although many of our discussions in this chapter are general we exemplify mainly using work done within the REWERSE working group on Adding Semantics to the Bioinformatics Web.

Place, publisher, year, edition, pages
Springer Berlin/Heidelberg, 2009 Edition: 1
Series
Lecture Notes in Computer Science, ISSN 0302-9743, E-ISSN 1611-3349 ; 5500
Keywords
semantic web, ontologies, standards, bioinformatics
National Category
Computer Sciences
Identifiers
urn:nbn:se:liu:diva-28207 (URN)10.1007/978-3-642-04581-3_8 (DOI)978-3-642-04580-6 (ISBN)
Available from: 2009-10-09 Created: 2009-10-09 Last updated: 2018-02-20Bibliographically approved
Lambrix, P., Liu, Q. & Tan, H. (2009). Repairing the missing is-a structure of ontologies (1ed.). In: Asunción Gómez-Pérez, Yong Yu and Ying Ding (Ed.), The Semantic Web Fourth Asian Conference, ASWC 2009, Shanghai, China, December 6-9, 2009. Proceedings: . Paper presented at 4th Asian Semantic Web Conference, 6-9 December, Shanghai, China (pp. 76-90). Springer Berlin/Heidelberg
Open this publication in new window or tab >>Repairing the missing is-a structure of ontologies
2009 (English)In: The Semantic Web Fourth Asian Conference, ASWC 2009, Shanghai, China, December 6-9, 2009. Proceedings / [ed] Asunción Gómez-Pérez, Yong Yu and Ying Ding, Springer Berlin/Heidelberg, 2009, 1, p. 76-90Conference paper, Published paper (Refereed)
Abstract [en]

Developing ontologies is not an easy task and often the resultingontologies are not consistent or complete. Such ontologies,although often useful, also lead to problems when used insemantically-enabled applications. Wrong conclusions may bederived or valid conclusions may be missed. To deal with thisproblem we may want to repair the ontologies. Up to date most workhas been performed on finding and repairing the semantic defectssuch as unsatisfiable concepts and inconsistent ontologies. Inthis paper we tackle the problem of repairing modeling defects andin particular, the repairing of structural relations (is-ahierarchy) in the ontologies. We study the case where missing is-arelations are given. We define the notion of a structural repairand develop algorithms to compute repairing actions that wouldallow deriving the missing is-a relations in the repairedontology. Further, we define preferences between repairs. We alsolook at how we can use external knowledge to recommend repairingactions to a domain expert. Further, we discuss an implementedprototype and its use as well as an experiment using theontologies of the Anatomy track of the Ontology AlignmentEvaluation Initiative.

Place, publisher, year, edition, pages
Springer Berlin/Heidelberg, 2009 Edition: 1
Series
Lecture Notes in Computer Science, ISSN 0302-9743, E-ISSN 1611-3349 ; 5926
National Category
Engineering and Technology
Identifiers
urn:nbn:se:liu:diva-28212 (URN)10.1007/978-3-642-10871-6_6 (DOI)000280398800006 ()978-3-642-10870-9 (ISBN)
Conference
4th Asian Semantic Web Conference, 6-9 December, Shanghai, China
Available from: 2009-10-09 Created: 2009-10-09 Last updated: 2018-11-27Bibliographically approved
Lambrix, P., Liu, Q. & Tan, H. (2009). RepOSE: an environment for repairing missing ontological structure (1ed.). In: Asunción Gómez-Pérez, Yong Yu, Ying Ding (Ed.), The Semantic Web Fourth Asian Conference, ASWC 2009, Shanghai, China, December 6-9, 2009. Proceedings: . Paper presented at Fourth Asian Conference (ASWC 2009), Shanghai, China, December 6-9, 2009 (pp. 365-366). Springer Berlin/Heidelberg
Open this publication in new window or tab >>RepOSE: an environment for repairing missing ontological structure
2009 (English)In: The Semantic Web Fourth Asian Conference, ASWC 2009, Shanghai, China, December 6-9, 2009. Proceedings / [ed] Asunción Gómez-Pérez, Yong Yu, Ying Ding, Springer Berlin/Heidelberg, 2009, 1, p. 365-366Conference paper, Published paper (Refereed)
Abstract [en]

Developing ontologies is not an easy task and often the resultingontologies are not consistent or complete. Such ontologies,although often useful, also lead to problems when used insemantically-enabled applications. Wrong conclusions may bederived or valid conclusions may be missed. To deal with thisproblem we may want to repair the ontologies. Up to date most workhas been performed on finding and repairing the semantic defectssuch as unsatisfiable concepts and inconsistent ontologies. Inthis paper we tackle the problem of repairing modeling defects andin particular, the repairing of structural relations (is-ahierarchy) in the ontologies. We study the case where missing is-arelations are given. We define the notion of a structural repairand develop algorithms to compute repairing actions that wouldallow deriving the missing is-a relations in the repairedontology. Further, we define preferences between repairs. We alsolook at how we can use external knowledge to recommend repairingactions to a domain expert. Further, we discuss an implementedprototype and its use as well as an experiment using theontologies of the Anatomy track of the Ontology AlignmentEvaluation Initiative.

Place, publisher, year, edition, pages
Springer Berlin/Heidelberg, 2009 Edition: 1
Series
Lecture Notes in Computer Science, ISSN 0302-9743, E-ISSN 1611-3349 ; 5926
National Category
Engineering and Technology
Identifiers
urn:nbn:se:liu:diva-28213 (URN)10.1007/978-3-642-10871-6_26 (DOI)000280398800026 ()978-3-642-10870-9 (ISBN)978-3-642-10871-6 (ISBN)
Conference
Fourth Asian Conference (ASWC 2009), Shanghai, China, December 6-9, 2009
Available from: 2009-10-09 Created: 2009-10-09 Last updated: 2018-11-27Bibliographically approved
Tan, H. & Lambrix, P. (2009). Selecting an ontology for biomedical text mining. In: 17th Conference on Intelligent Systems for Molecular Biology: . Paper presented at 17th Conference on Intelligent Systems for Molecular Biology.
Open this publication in new window or tab >>Selecting an ontology for biomedical text mining
2009 (English)In: 17th Conference on Intelligent Systems for Molecular Biology, 2009Conference paper, Poster (with or without abstract) (Refereed)
National Category
Engineering and Technology
Identifiers
urn:nbn:se:liu:diva-59905 (URN)
Conference
17th Conference on Intelligent Systems for Molecular Biology
Available from: 2010-09-29 Created: 2010-09-29 Last updated: 2015-04-30
Organisations

Search in DiVA

Show all publications