Paper: Automatic prediction of aspectual class of verbs in context

ACL ID P14-2085
Title Automatic prediction of aspectual class of verbs in context
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2014
Authors

This paper describes a new approach to predicting the aspectual class of verbs in context, i.e., whether a verb is used in a stative or dynamic sense. We identify two challenging cases of this problem: when the verb is unseen in training data, and when the verb is ambiguous for aspec- tual class. A semi-supervised approach us- ing linguistically-motivated features and a novel set of distributional features based on representative verb types allows us to predict classes accurately, even for unseen verbs. Many frequent verbs can be either stative or dynamic in different contexts, which has not been modeled by previous work; we use contextual features to re- solve this ambiguity. In addition, we intro- duce two new datasets of clauses marked for aspectual class.