As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
Lexical entailment is knowledge that may prove very useful for a variety of applications that deal with information implicit in a text. In this paper we address the problem of automatic discovery of pairs of verbs related by entailment. A specific challenge in this task is recognition of the direction of entailment in a pair. We model entailment by a number of linguistic cues as to local coherence between clauses. We first investigate the effect of these cues on the quality of the model and then evaluate it against human judgements. Our evaluation reveals that the model is capable of correctly identifying the direction in entailment-related pairs, although their separation from bidirectional pairs proves a more difficult task.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.