An Information-Theoretic Definition of Similarity
ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
Addressing ontology-based question answering with collections of user queries
Information Processing and Management: an International Journal
Evaluating the inferential utility of lexical-semantic resources
EACL '09 Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics
Extracting paraphrase patterns from bilingual parallel corpora
Natural Language Engineering
Syntactic/semantic structures for textual entailment recognition
HLT '10 Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Types of common-sense knowledge needed for recognizing textual entailment
HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: short papers - Volume 2
Detecting apposition for text simplification in basque
CICLing'13 Proceedings of the 14th international conference on Computational Linguistics and Intelligent Text Processing - Volume 2
| Hi-index | 0.00 |
We compare two approaches to the problem of Textual Entailment: SLIM, a compositional approach modeling the task based on identifying relations in the entailment pair, and BoLI, a lexical matching algorithm. SLIM's framework incorporates a range of resources that solve local entailment problems. A search-based inference procedure unifies these resources, permitting them to interact flexibly. BoLI uses WordNet and other lexical similarity resources to detect correspondence between related words in the Hypothesis and the Text. In this paper we describe both systems in some detail and evaluate their performance on the 3rd PASCAL RTE Challenge. While the lexical method outperforms the relation-based approach, we argue that the relation-based model offers better long-term prospects for entailment recognition.