2026-07-23T05:31:15Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:10876 2024-03-06T10:30:44Z ddc:004 open_access

From Lexical to Semantic Features in Paraphrase Identification Fialho, Pedro Coheur, Luísa Quaresma, Paulo paraphrase identification lexical features syntactic features semantic features The task of paraphrase identification has been applied to diverse scenarios in Natural Language Processing, such as Machine Translation, summarization, or plagiarism detection. In this paper we present a comparative study on the performance of lexical, syntactic and semantic features in the task of paraphrase identification in the Microsoft Research Paraphrase Corpus. In our experiments, semantic features do not represent a gain in results, and syntactic features lead to the best results, but only if combined with lexical features. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Pedro Fialho and Luísa Coheur and Paulo Quaresma 2019 Is Part Of OASIcs, Volume 74, 8th Symposium on Languages, Applications and Technologies (SLATE 2019) InProceedings Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/OASIcs.SLATE.2019.9 urn:nbn:de:0030-drops-108763 https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.SLATE.2019.9 eng https://creativecommons.org/licenses/by/3.0/legalcode