bla bla bla bla bla
Roser Morante - academic web page - research

Home
Home

Research
Research

Publications
Publications

Activities
Activities

Links
Links

Links
Links biomedical text mining



Keywords: machine learning, natural language processing, text mining, processing modality and negation, semantic role labeling, extraction of semantic relations, extraction of biomedical relations.

Interests
I am interested in applying supervised and unsupervised techniques to semantics-oriented natural language processing tasks, like semantic role labeling, semantic relation finding, coreference resolution, paraphrasing, textual entailment, summarization, dialogue-act recognition, etc.

At this moment I am working mostly on biomedical text mining: processing negation and modality, extraction of biomedical events, PPI, semantic role labeling and coreference resolution in biomedical texts.
Current project
  • BIOGRAPH: Text Mining on heterogeneous knowledge bases. An application to optimised discovery of disease relevant genetic variants.

    • The BIOGRAPH project aims at putting forward a new methodology for text mining from heterogeneous information sources that will be used to assist researchers in ranking candidate disease causing genes. The final goal of the project is to show new results in mining for previously unknown relations between genes and phenotypes, and improved gene prioritisation finding non-obvious disease causing genes. It is a multidisciplinary project within the University of Antwerp carried out in collaboration with the research group AMG (Applied Molecular Genomics) from the Department of Molecular Genetics and with the ADReM research group of the Department of Mathematics and Computer Science.

    BiographTA is the part of the project aimed at providing text mining solutions.

    Publications

    R. Morante and Caroline Sporleder (2010) (Eds.) Proceedings of the Workshop on Negation and Speculation in Natural Language Processing Uppsala, Sweden. [pdf]

    Th. Abeel, S. Van Landeghem, R. Morante, V. Van Asch, Y. Van de Peer, W. Daelemans, and Yvan Saeys (2010) Highlights of the BioTM 2010 workshop on advances in bio text mining BMC Bioinformatics 2010, 11(Suppl 5):I1 [pdf]

    V. Van Asch, R. Morante, and W. Daelemans (2010) Towards improving the precision of a relation extraction system by processing negation and speculation. Proceedings of the 4th Symposium on Semantic Mining in Biomedicine (SMBM), pages 164-165. Hinxton, UK.

    D. Rebholz-Schuhmann, A. Jimeno, Ch. Li, S. Kafkas, I. Lewin, N. Kang, P. Corbett, D. Milward, E. Buyko, E. Beisswanger, K. Hornbostel, A. Kouznetsov, R. Witte, J. B. Laurila, Ch. JO Baker, Ch. Kuo, S. Clematide, F. Rinaldi, R. Farkas, G. Móra, K. Hara, L. Furlong, M. Rautschka, M. Lara Neves, A. Pascual-Montano, Q. Wei, N. Collier, F. Mahbub Chowdhury, A. Lavelli, R. Berlanga, R. Morante, V. Van Asch, W. Daelemans, J. L. Marina, E. van Mulligen, J. Kors and U. Hahn (2010) Assessment of NER solutions against the first and second CALBC Silver Standard Corpus. Proceedings of the 4th Symposium on Semantic Mining in Biomedicine (SMBM), pages 66-74. Hinxton, UK.

    W. Daelemans, V. Van Asch, and R. Morante (2010) Memory-based biomedical named-entity tagging. Proceedings of the First CALBC Workshop. EBI, Cambridgeshire, UK, pp. 31-32. [pdf]

    R. Morante, V. Van Asch, and W. Daelemans (2010) Memory-based resolution of in-sentence scopes of hedge cues. Proceedings of the Fourteenth Conference on Computational Natural Language Learning: Shared Task, pages 40-47, Uppsala, Sweden. Association for Computational Linguistics. [pdf]

    R. Morante (2010) Semantic role labeling of gene regulation events: preliminary results.Proceedings of the 2010 Workshop on Biomedical Natural Language Processing, ACL 2010, pages 126-127, Uppsala, Sweden. Association for Computational Linguistics. [pdf]

    R. Morante (2010) Descriptive analysis of negation cues in biomedical texts. Proceedings of the Seventh International Language Resources and Evaluation (LREC'10), pp. 1429-1436. Valletta, Malta. [pdf]

    J. Ruppenhofer, C. Sporleder, R. Morante, C. Baker, and M. Palmer (2010) SemEval-2010 Task 10: Linking Events and Their Participants in Discourse. Proceedings of the 5th International Workshop on Semantic Evaluation, ACL 2010, pages 45-50, Uppsala, Sweden, July 2010. Association for Computational Linguistics. [pdf]

    R. Morante and W. Daelemans (2009). A metalearning approach to processing the scope of negation. Proc. of CoNLL 2009, Boulder, Colorado. [pdf]

    R. Morante and W. Daelemans (2009). Learning the scope of hedge cues in biomedical texts. Proc. of BioNLP 2009, Boulder, Colorado. [pdf]

    R. Morante, V. Van Asch, and W. Daelemans (2009). A memory-based learning approach to event extraction in biomedical texts. Proc. of the BioNLP Shared Task 2009, Boulder, Colorado. [pdf]

    R. Morante, V. Van Asch, and A. van den Bosch (2009). Dependency Parsing and Semantic Role Labeling as a Single Task. Proceedings of the 7th International Conference on Recent Advances in Natural Language Processing, pp 275-280. Borovets, Bulgaria. [ pdf]

    R. Morante, V. Van Asch, and A. van den Bosch (2009). Joint memory-based learning of syntactic and semantic dependencies in multiple languages. Proc. of the CoNLL Shared Task 2009, Boulder, Colorado. [pdf]

    J. Ruppenhofer, C. Sporleder, R. Morante, C. Baker, and M. Palmer (2009). The SemEval-2010 Task on Linking Events and Their Participants in Discourse. Proc. of SEW 2009, Boulder, Colorado. [pdf]

    Roser Morante, Walter Daelemans, and Vincent Van Asch (2008). A Combined Memory-Based Semantic Role Labeler of English. Proceedings of the 12th Conference on Computational Natural Language Learning., pp. 208-212. [pdf]

    Roser Morante, Anthony Liekens, and Walter Daelemans (2008). Learning the Scope of Negation in Biomedical Texts. Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing., pp. 715-724. [pdf]

    Past projects
  • Semi-automatic techniques for semantic role labeling applied to a Spanish corpus

    • Two-year postdoc project funded by the Spanish Ministry of Education. The project focuses on developing a semantic role labeling system for Spanish. In the first phase of the project an eighty thousand word corpus was annotated with syntactic dependencies and semantic roles. This corpus has been used to train several memory-based semantic role labelers that will be used to annotate semi-automatically a seventy million word corpus using active learning techniques.

    Publications

    R. Morante and A. van den Bosch (2009). Feature construction for memory-based semantic role labeling of Catalan and Spanish. In Recent Advances in Natural Language Processing V. Current Issues in Linguistic Theory 309. John Benjamins. Pages 131-142.

    M. Surdeanu, R. Morante, and Ll. Màrquez (2008). Analysis of Joint Inference Strategies for the Semantic Role Labeling of Spanish and Catalan. Proceedings of the Computational Linguistics and Intelligent Text Processing 9th International Conference, CICLing 2008. Lecture Notes in Computer Science vol. 4919/2008, Springer, Berlin/Heidelberg, pp. 206-218.

    R. Morante (2008). Semantic role labeling tools trained on the Cast3LB-CoNLL-SemRol corpus. Proceedings of the Sixth International Language Resources and Evaluation (LREC'08). Marrakech, Morocco, 2008. [pdf]

    R. Morante (2008). Etiquetat automàtic de rols semàntics amb un sistema basat en memòria. Digithum vol. 10. [link]

    R. Morante (2008). Experiments with an ensemble of Spanish dependency parsers. Procesamiento del Lenguaje Natural vol. 40, pp. 59-66. [pdf]

    R. Morante and A. van den Bosch (2007). Memory-based semantic role labeling. Proceedings of the International Conference Recent Advances in Natural Language Processing, Borovets, Bulgary, pp. 388-394. [pdf]

    R. Morante and B. Busser (2007). Semantic role labeling of Catalan and Spanish using TiMBL. Proceedings of the 4th International Workshop on Semantic Evaluations (SEMEVAL), Prague, Czec Republic, pp.183-186. [pdf]

    I. Hendricx, R. Morante, C. Sporleder, and A. Van den Bosch (2007). ILK: Machine learning of semantic relations with shallow features and almost no data. Proceedings of the 4th International Workshop on Semantic Evaluations (SEMEVAL), Prague, Czec Republic, pp. 187-190. [pdf]

    R. Morante and B. Busser (2007). Semantic role labeling based on TiMBL. Notes of the Workshop on Machine Learning for Natural Language Processing, Amsterdam, The Netherlands, pp. 21-22.

    R. Morante (2006). Semantic role annotation in the Cast3LB-CoNLL-SemRol corpus. Technical Report ILK 06-03. Tilburg University. [pdf]

    B. Busser and R.Morante (2005). Designing an active learning based system for corpus annotation. Procesamiento del Lenguaje Natural, Revista n. 35, pp. 375-382. [pdf]

  • Computing meaning in interaction

    • The general purpose of the project was to define a model of dialogue context update in the framework of Dynamic Interpretation Theory (DIT). The main contributions of the project were: (i) applying the theory to the analysis of dialogue, using the DIT taxonomy of dialogue acts to model dialogues; the effects of three groups of dialogue acts in the dialogue context were modeled: Information Transfer, Action Discussion, and Dialogue Control Feedback; (ii) assigning the model of beliefs and goals to dialogue acts; (iii) analysing fragments of dialogues by applying this model; (iv) defining a model of context update by defining certain principles and rules. On the basis of a detailed analysis of the flow of beliefs in a number of simple dialogue fragments, certain mechanisms for modeling the transfer of information were proposed: adoption, strengthening, and cancellation of beliefs. A result of the project was to explain in the form of an algorithm how information may be updated in a dialogue, in particular how information may be grounded. The context update model was converted into an algorithm and implemented in a dialogue simulator.

    Publications

    R. Morante (2007). Computing Meaning in Interaction. PhD Dissertation, Tilburg University.

    H. Bunt, R.Morante, and S. Keizer (2007). An empirically based computational model of grounding in dialogue. Proceedings of the 8th SIGDIAL Workshop on Discourse and Dialogue. Antwerp, Belgium, pp. 283-290. [pdf]

    H. Bunt and R. Morante (2007). The Weakest Link. Text, Speech and Dialogue, 10th International Conference, TSD 2007, Proceedings. Lecture Notes in Computer Science, 4629, Springer, Pilzen, Czech Republic, pp. 591-598. [pdf]

    R. Morante, S. Keizer, and H. Bunt (2007). A dialogue act based model for context updating. Proceedings of the 11th Workshop on the Semantics and Pragmatics of Dialogue (Decalog 2007), Rovereto, Italy, pp. 9-16. [pdf]

    S. Keizer and R. Morante (2007) Dialogue simulation and context dynamics for dialogue management. Proceedings of the 16th Nordic Conference of Computational Linguistics, NODALIDA 2007, University of Tartu, Estonia, pp. 310-317. [pdf]

    S. Keizer and R. Morante (2006). Context specification and update mechanisms for dialogue management. Proceedings of the 18th BeNeLux Conference on Artificial Intelligence BNAIC'06. Namur, Belgium, pp. 181-188. [pdf]

    R. Morante and S. Keizer (2006). DISCUS: a dialogue simulation and context update system. Proceedings of the 10th workshop on the Semantics and Pragmatics of Dialogue (brandial'06), Potsdam, pp. 169-170. [pdf]

    S. Keizer and R. Morante (2006). Dialogue acts as context operators constraining the generation of dialogical discourse. Proceedings of the Workshop on Constraints on Discourse, Maynooth, Ireland, pp. 117-124. [pdf]