ABSTRACT
In previous research in automatic verb classification, syntactic features have proved the most useful features, although manual classifications rely heavily on semantic features. We show, in contrast with previous work, that considerable additional improvement can be obtained by using semantic features in automatic classification: verb selectional preferences acquired from corpus data using a fully unsupervised method. We report these promising results using a new framework for verb clustering which incorporates a recent subcategorization acquisition system, rich syntactic-semantic feature sets, and a variation of spectral clustering which performs particularly well in high dimensional feature space.
- Shane Bergsma, Dekang Lin, and Randy Goebel. Discriminative learning of selectional preference from unlabeled text. In Proc. of EMNLP, 2008. Google ScholarDigital Library
- Chris Brew and Sabine Schulte im Walde. Spectral clustering for german verbs. In Proc. of EMNLP, 2002. Google ScholarDigital Library
- Ted Briscoe, John Carroll, and Rebecca Watson. The second release of the rasp system. In Proc. of the COLING/ACL on Interactive presentation sessions, 2006. Google ScholarDigital Library
- Carsten Brockmann and Mirella Lapata. Evaluating and combining approaches to selectional preference acquisition. In Proc. of EACL, 2003. Google ScholarDigital Library
- Jinxiu Chen, Dong-Hong Ji, Chew Lim Tan, and Zheng-Yu Niu. Unsupervised relation disambiguation using spectral clustering. In Proc. of COLING/ACL, 2006. Google ScholarDigital Library
- Hoa Trang Dang. Investigations into the Role of Lexical Semantics in Word Sense Disambiguation. PhD thesis, CIS, University of Pennsylvania, 2004.Google Scholar
- Katrin Erk. A simple, similarity-based model for selectional preferences. In Proc. of ACL, 2007.Google Scholar
- David Graff. North american news text corpus. Linguistic Data Consortium, 1995.Google Scholar
- Eric Joanis. Automatic Verb Classification Using a General Feature Space. Master's thesis, University of Toronto, 2002.Google Scholar
- Eric Joanis, Suzanne Stevenson, and David James. A general feature space for automatic verb classification. Natural Language Engineering, 2008. Google ScholarDigital Library
- Karin Kipper-Schuler. VerbNet: A broad-coverage, comprehensive verb lexicon. 2005.Google Scholar
- Anna Korhonen, Yuval Krymolowski, and Ted Briscoe. A large subcategorization lexicon for natural language processing applications. In Proc. of the 5th LREC, 2006.Google Scholar
- Anna Korhonen, Yuval Krymolowski, and Nigel Collier. The Choice of Features for Classification of Verbs in Biomedical Texts. In Proc. of COLING, 2008. Google ScholarDigital Library
- Claudia Kunze and Lothar Lemnitzer. GermaNet-representation, visualization, application. In Proc. of LREC, 2002.Google Scholar
- Lillian. Lee. On the effectiveness of the skew divergence for statistical language analysis. In Artificial Intelligence and Statistics, 2001.Google Scholar
- Geoffrey Leech. 100 million words of english: the british national corpus. Language Research, 1992.Google Scholar
- Beth. Levin. English verb classes and alternations: A preliminary investigation. Chicago, IL, 1993.Google Scholar
- Jianguo Li and Chris Brew. Which Are the Best Features for Automatic Verb Classification. In Proc. of ACL, 2008.Google Scholar
- Diana McCarthy. Lexical Acquisition at the Syntax-Semantics Interface: Diathesis Alternations, Sub-categorization Frames and Selectional Preferences. PhD thesis, University of Sussex, UK, 2001.Google Scholar
- Marina. Meila. The multicut lemma. Technical report, University of Washington, 2001.Google Scholar
- Marina Meila and Jianbo Shi. A random walks view of spectral segmentation. AISTATS, 2001.Google Scholar
- George A. Miller. WordNet: a lexical database for English. Communications of the ACM, 1995. Google ScholarDigital Library
- Pedro J. Moreno, Purdy P. Ho, and Nuno Vasconcelos. A Kullback-Leibler divergence based kernel for SVM classification in multimedia applications. In Proc. of NIPS, 2004.Google Scholar
- Andrew Y. Ng, Michael Jordan, and Yair Weiss. On spectral clustering: Analysis and an algorithm. In Proc. of NIPS, 2002.Google ScholarDigital Library
- Diarmuid Ó Séaghdha and Ann Copestake. Semantic classification with distributional kernels. In Proc. of COLING, 2008. Google ScholarDigital Library
- Judita Preiss, Ted Briscoe, and Anna Korhonen. A system for large-scale acquisition of verbal, nominal and adjectival subcategorization frames from corpora. In Proc. of ACL, 2007.Google Scholar
- Jan Puzicha, Thomas Hofmann, and Joachim M. Buhmann. A theory of proximity based clustering: Structure detection by optimization. Pattern Recognition, 2000.Google Scholar
- Sabine Schulte im Walde. Experiments on the automatic induction of german semantic verb classes. Computational Linguistics, 2006. Google ScholarDigital Library
- Sabine Schulte im Walde, Christian Hying, Christian Scheible, and Helmut Schmid. Combining EM Training and the MDL Principle for an Automatic Verb Classification incorporating Selectional Preferences. In Proc. of ACL, pages 496--504, 2008.Google Scholar
- Lei Shi and Rada Mihalcea. Putting pieces together: Combining FrameNet, VerbNet and WordNet for robust semantic parsing. In Proc. of CICLING, 2005.Google ScholarDigital Library
- Suzanne Stevenson and Eric Joanis. Semi-supervised verb class discovery using noisy features. In Proc. of HLT-NAACL 2003, pages 71--78, 2003. Google ScholarDigital Library
- Lin Sun, Anna Korhonen, and Yuval Krymolowski. Verb class discovery from rich syntactic data. Lecture Notes in Computer Science, 4919:16, 2008. Google ScholarDigital Library
- Robert Swier and Suzanne Stevenson. Unsupervised semantic role labelling. In Proc. of EMNLP, 2004.Google Scholar
- Deepak Verma and Marina Meila. Comparison of spectral clustering methods. Advances in Neural Information Processing Systems (NIPS 15), 2003.Google Scholar
- Andreas Vlachos, Anna Korhonen, and Zoubin Ghahramani. Unsupervised and constrained dirichlet process mixture models for verb clustering. In Proc. of the Workshop on Geometrical Models of Natural Language Semantics, 2009. Google ScholarDigital Library
- Ulrike von Luxburg. A tutorial on spectral clustering. Statistics and Computing, 2007. Google ScholarDigital Library
- Beñat Zapirain, Eneko Agirre, and Lluís Màrquez. Robustness and generalization of role sets: PropBank vs. VerbNet. In Proc. of ACL, 2008.Google Scholar
Index Terms
- Improving verb clustering with automatically acquired selectional preferences
Recommendations
Disambiguating noun and verb senses using automatically acquired selectional preferences
SENSEVAL '01: The Proceedings of the Second International Workshop on Evaluating Word Sense Disambiguation SystemsOur system for the Senseval-2 all words task uses automatically acquired selectional preferences to sense tag subject and object head nouns, along with the associated verbal predicates. The selectional preferences comprise probability distributions over ...
Disambiguating Nouns, Verbs, and Adjectives Using Automatically Acquired Selectional Preferences
Selectional preferences have been used by word sense disambiguation (WSD) systems as one source of disambiguating information. We evaluate WSD using selectional preferences acquired for English adjective-noun, subject, and direct object grammatical ...
Inferring selectional preferences from part-of-speech N-grams
EACL '12: Proceedings of the 13th Conference of the European Chapter of the Association for Computational LinguisticsWe present the PONG method to compute selectional preferences using part-of-speech (POS) N-grams. From a corpus labeled with grammatical dependencies, PONG learns the distribution of word relations for each POS N-gram. From the much larger but unlabeled ...
Comments