Selection and information: a class-based approach to lexical relationships
Selection and information: a class-based approach to lexical relationships
WordNet: a lexical database for English
Communications of the ACM
DIRT @SBT@discovery of inference rules from text
Proceedings of the seventh ACM SIGKDD international conference on Knowledge discovery and data mining
SCIE '97 International Summer School on Information Extraction: A Multidisciplinary Approach to an Emerging Information Technology
Word association norms, mutual information, and lexicography
ACL '89 Proceedings of the 27th annual meeting on Association for Computational Linguistics
Automatic acquisition of hyponyms from large text corpora
COLING '92 Proceedings of the 14th conference on Computational linguistics - Volume 2
Learning surface text patterns for a Question Answering system
ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Discovering entailment relations using "textual entailment patterns"
EMSEE '05 Proceedings of the ACL Workshop on Empirical Modeling of Semantic Equivalence and Entailment
Using hidden Markov random fields to combine distributional and pattern-based word clustering
COLING '08 Proceedings of the 22nd International Conference on Computational Linguistics - Volume 1
Hi-index | 0.00 |
Verbs represent a way in which ontological relationships between concepts and instances are expressed in natural language utterances. Moreover, an organized network of semantically related verbs can play a crucial role in applications. For example, if a Question-Answering system could exploit the direction of the entailment relation win → play, it may expand the question “Who played against Liverpool?” with “X won against Liverpool” and it may avoid the expansion of “Who won against Liverpool?” in “X played against Liverpool” that would be wrong. In this paper, we present a survey of the methods proposed to extract verb relations in corpora. These methods can be divided in two classes: those using the Harris distributional hypothesis and those based on point-wise assertions. These methods are analysed and compared.