Abstract
In this paper we define two intermediate models of textual entailment, which correspond to lexical and lexical-syntactic levels of representation. We manually annotated a sample from the RTE dataset according to each model, compared the outcome for the two models, and explored how well they approximate the notion of entailment. We show that the lexicalsyntactic model outperforms the lexical model, mainly due to a much lower rate of false-positives, but both models fail to achieve high recall. Our analysis also shows that paraphrases stand out as a dominant contributor to the entailment task. We suggest that our models and annotation methods can serve as an evaluation scheme for entailment at these levels.
| Original language | English |
|---|---|
| Pages | 55-60 |
| Number of pages | 6 |
| State | Published - 2005 |
| Event | 2005 ACL Workshop on Empirical Modeling of Semantic Equivalence and Entailment, EMSEE 2005 - Ann Arbor, United States Duration: 30 Jun 2005 → … |
Conference
| Conference | 2005 ACL Workshop on Empirical Modeling of Semantic Equivalence and Entailment, EMSEE 2005 |
|---|---|
| Country/Territory | United States |
| City | Ann Arbor |
| Period | 30/06/05 → … |
Bibliographical note
Publisher Copyright:© 2005 Association for Computational Linguistics.
Funding
We would like to thank Ido Dagan for helpful discussions and for his scientific supervision. This work was supported in part by the IST Programme of the European Community, under the PASCAL Network of Excellence, IST-2002-506778. This publication only reflects the authors’ views.