Abstract
We improve the quality of paraphrases extracted from parallel corpora by requiring that phrases and their paraphrases be the same syntactic type. This is achieved by parsing the English side of a parallel corpus and altering the phrase extraction algorithm to extract phrase labels alongside bilingual phrase pairs. In order to retain broad coverage of non-constituent phrases, complex syntactic labels are introduced. A manual evaluation indicates a 19% absolute improvement in paraphrase quality over the baseline method. © 2008 Association for Computational Linguistics.
Cite
CITATION STYLE
Callison-Burch, C. (2008). Syntactic constraints on paraphrases extracted from parallel corpora. In EMNLP 2008 - 2008 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference: A Meeting of SIGDAT, a Special Interest Group of the ACL (pp. 196–205). Association for Computational Linguistics (ACL). https://doi.org/10.3115/1613715.1613743
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
