Creative Commons Attribution 3.0 Unported license (CC-BY 3.0)when quoting this document, please refer to the following
DOI: 10.4230/OASIcs.SLATE.2019.9
URN: urn:nbn:de:0030-drops-108763
URL: https://drops.dagstuhl.de/opus/volltexte/2019/10876/
Fialho, Pedro ; Coheur, Luísa ; Quaresma, Paulo
From Lexical to Semantic Features in Paraphrase Identification
| pdf-format: |
|
Abstract
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.
BibTeX - Entry
@InProceedings{fialho_et_al:OASIcs:2019:10876,
author = {Pedro Fialho and Lu{\'\i}sa Coheur and Paulo Quaresma},
title = {{From Lexical to Semantic Features in Paraphrase Identification}},
booktitle = {8th Symposium on Languages, Applications and Technologies (SLATE 2019)},
pages = {9:1--9:11},
series = {OpenAccess Series in Informatics (OASIcs)},
ISBN = {978-3-95977-114-6},
ISSN = {2190-6807},
year = {2019},
volume = {74},
editor = {Ricardo Rodrigues and Jan Janousek and Lu{\'\i}s Ferreira and Lu{\'\i}sa Coheur and Fernando Batista and Hugo Gon{\c{c}}alo Oliveira},
publisher = {Schloss Dagstuhl--Leibniz-Zentrum fuer Informatik},
address = {Dagstuhl, Germany},
URL = {http://drops.dagstuhl.de/opus/volltexte/2019/10876},
URN = {urn:nbn:de:0030-drops-108763},
doi = {10.4230/OASIcs.SLATE.2019.9},
annote = {Keywords: paraphrase identification, lexical features, syntactic features, semantic features}
}
| Keywords: | paraphrase identification, lexical features, syntactic features, semantic features | |
| Seminar: | 8th Symposium on Languages, Applications and Technologies (SLATE 2019) | |
| Issue date: | 2019 | |
| Date of publication: | 24.07.2019 |
