Abstract
A reasonably simple, domain-independent, large-scale approach of lexical semantics to paraphrase recognition is presented in this paper. It relies on the enrichment of morpho-syntactic rules and the addition of four boolean syntactico-semantic features to a set of 1,023 words. It results in a signi cant enhancement of precision of 30% with a slight decrease in recall of 10%.
Cite
CITATION STYLE
Fabre, C., & Jacquemin, C. (2000). Boosting Variant Recognition with Light Semantics. In 18th International Conference on Computational Linguistics, COLING 2000 - Proceedings of Science (Vol. 1, pp. 264–270). Association for Computational Linguistics (ACL). https://doi.org/10.3115/990820.990859
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.