Cristina Nicolae
ABSTRACT
In this paper we present a semantic architecture that was employed for processing two different SemEval 2007 tasks: Task 4 (Classification of Semantic Relations between Nominals) and Task 8 (Metonymy Resolution). The architecture uses multiple forms of syntactic, lexical, and semantic information to inform a classification-based approach that generates a different model for each machine learning algorithm that implements the classification. We used decision trees, decision rules, logistic regression and lazy classifiers. A voting module selects the best performing module for each task evaluated in SemEval 2007. The paper details the results obtained when using the semantic architecture.
- Marie-Catherine de Marneffe, Bill MacCartney, and Christopher D. Manning. 2006. Generating typed dependency parses from phrase structure parses. In 5th International Conference on Language Resources and Evaluation (LREC 2006).Google Scholar
- C. Fellbaum, editor. 1998. WordNet: An Electronic Lexical Database and Some of its Applications. MIT Press.Google Scholar
- Roxana Girju, Dan Moldovan, Marta Tatu, and Daniel Antohe. 2005. On the semantics of noun compounds. In Computer Speech and Language, volume 19, pages 479--496. Google ScholarDigital Library
- Roxana Girju, Marti Hearst, Preslav Nakov, Vivi Nastase, Stan Szpakowicz, Peter Turney, and Deniz Yuret. 2007. Task 04: Classification of semantic relations between nominal at semeval 2007. In SemEval 2007. Google ScholarDigital Library
- Beth Levin. 1993. English Verb Classes and Alternations. The University of Chicago Press, Chicago and London.Google Scholar
- Katja Markert and Malvina Nissim. 2002. Metonymy resolution as a classification task. In the 2002 Conference on Empirical Methods in Natural LAnguage Processing (EMNLP2002). Google ScholarDigital Library
- Katja Markert and Malvina Nissim. 2007. Task 08: Metonymy resolution at semeval 2007. In SemEval 2007. Google ScholarDigital Library
- Mihai Surdeanu and Jordi Turmo. 2005. Semantic role labeling using complete syntactic analysis. In CoNLL 2005, Shared Task. Google ScholarDigital Library
- David Traum and Nizar Habash. 2000. Generation from lexical conceptual structure. In Workshop on Applied Interlinguas, ANLP-2000. Google ScholarDigital Library
- Ian H. Witten and Eibe Frank. 2005. Data Mining: Practical machine learning tools and techniques. Morgan Kaufmann, 2nd edition. Google ScholarDigital Library
- UTD-HLT-CG: semantic architecture for metonymy resolution and classification of nominal relations
Recommendations
UTD: Classifying semantic relations by combining lexical and semantic resources
SemEval '10: Proceedings of the 5th International Workshop on Semantic EvaluationThis paper describes our system for SemEval-2010 Task 8 on multi-way classification of semantic relations between nominals. First, the type of semantic relation is classified. Then a relation type-specific classifier determines the relation direction. ...
UTD-SRL: a pipeline architecture for extracting frame semantic structures
SemEval '07: Proceedings of the 4th International Workshop on Semantic EvaluationsThis paper describes our system for the task of extracting frame semantic structures in SemEval--2007. The system architecture uses two types of learning models in each part of the task: Support Vector Machines (SVM) and Maximum Entropy (ME). Designed as ...
UTD: determining relational similarity using lexical patterns
SemEval '12: Proceedings of the First Joint Conference on Lexical and Computational Semantics - Volume 1: Proceedings of the main conference and the shared task, and Volume 2: Proceedings of the Sixth International Workshop on Semantic EvaluationIn this paper we present our approach for assigning degrees of relational similarity to pairs of words in the SemEval-2012 Task 2. To measure relational similarity we employed lexical patterns that can match against word pairs within a large corpus of ...
Comments