Assisting Pictogram Selection with Categorized Semantics
IEICE - Transactions on Information and Systems
IXIR: A statistical information distillation system
Computer Speech and Language
BioNLP '08 Proceedings of the Workshop on Current Trends in Biomedical Natural Language Processing
Prepositions in applications: A survey and introduction to the special issue
Computational Linguistics
Online entropy-based model of lexical category acquisition
CoNLL '10 Proceedings of the Fourteenth Conference on Computational Natural Language Learning
Semantic role patterns and verb classes in verb valency lexicon
TSD'10 Proceedings of the 13th international conference on Text, speech and dialogue
A survey of paraphrasing and textual entailment methods
Journal of Artificial Intelligence Research
Using syntactic and semantic based relations for dialogue act recognition
COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics: Posters
Minimum Description Length Penalization for Group and Multi-Task Sparse Learning
The Journal of Machine Learning Research
Gathering lexical linked data and knowledge patterns from FrameNet
Proceedings of the sixth international conference on Knowledge capture
DISCUSS: a dialogue move taxonomy layered over semantic representations
IWCS '11 Proceedings of the Ninth International Conference on Computational Semantics
Classifying Arabic verbs using sibling classes
IWCS '11 Proceedings of the Ninth International Conference on Computational Semantics
Crowd-based recognition of web interaction patterns
Adjunct proceedings of the 25th annual ACM symposium on User interface software and technology
Classifying French verbs using French and English lexical resources
ACL '12 Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers - Volume 1
Polarity Analysis for Food and Disease Relationships
WI-IAT '12 Proceedings of the The 2012 IEEE/WIC/ACM International Joint Conferences on Web Intelligence and Intelligent Agent Technology - Volume 01
IBM Journal of Research and Development
Automatic knowledge extraction from documents
IBM Journal of Research and Development
Automatic case acquisition from texts for process-oriented case-based reasoning
Information Systems
Hi-index | 0.01 |
Despite the proliferation of approaches to lexicon development, the field of natural language processing has yet to develop a clear consensus on guidelines for computational verb lexicons, which has severely limited their utility in information processing applications. James Pustejovsky's Generative Lexicon has concentrated on nouns rather than verbs. WordNet does not provide a comprehensive account of possible syntactic frames and predicate argument structures associated with individual verb senses and ComLex provides syntactic frames but ignores sense distinctions. Dorr's LCS lexicon attempts to address these limitations, but does not provide broad coverage of syntactic frames or different senses or links to actual instances in corpora. In order to address this gap, we created VerbNet, a verb lexicon compatible with Word-Net but with explicitly stated syntactic and semantic information, using Levin verb classes to systematically construct lexical entries. Classes are hierarchically organized to ensure that all their members have common semantic and syntactic properties. Each class in the hierarchy is characterized extensionally by its set of verbs, and intensionally by syntactic frames and semantic predicates and a list of typical verb arguments. One of VerbNet's primary applications has been as a basis for Parameterized Action Representations (PARs), which are used to animate the actions of virtual human agents in a simulated 3D environment. In order to support the animation of the actions, PARs have to make explicit many details that are often underspecified in the language. This detailed level of representation also provides a suitable pivot representation for generation in other natural languages, i.e., a form of interlingua. To evaluate VerbNet's syntactic coverage it has been mapped to the Proposition Bank. VerbNet syntactic frames account for over 84% exact matches to the frames found in PropBank. VerbNet provides mappings between its verbs and WordNet senses and between its verbs and FameNet II frames, and mappings between the syntactic frames and Xtag tree families. All these resources are complementary and can be used as extensions of each other. The original set of classes described by Levin has been refined and extended in many ways through systematic efforts: the coverage experiment against PropBank corpus instances proposed a large set of new syntactic frames and a better treatment of prepositions; new classes from Korhonen and Briscoe's resource were integrated into the lexicon; and new members from the LCS database were added. Taking advantage of VerbNet's class-based approach automatic acquisition methods were investigated. Additional verbs derived from Kingsbury's clustering experiments and from Loper's VerbNet-WordNet correlation experiment were integrated into the lexicon. These experiments show that it is possible to semi-automatically supplement and tune VerbNet with novel information from corpus data. These approaches reduce the manual classification and enable easy adaptation of the lexicon to specific tasks and applications.