ECNU: Leveraging Word Embeddings to Boost Performance for Paraphrase in Twitter

Jiang Zhao, Man Lan

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

12 Scopus citations

Abstract

This paper describes our approaches to paraphrase recognition in Twitter organized as task 1 in Semantic Evaluation 2015. Lots of approaches have been proposed to address the paraphrasing task on conventional texts (surveyed in (Madnani and Dorr, 2010)). In this work we examined the effectiveness of various linguistic features proposed in traditional paraphrasing task on informal texts, (i.e., Twitter), for example, string based, corpus based, and syntactic features, which served as input of a classification algorithm. Besides, we also proposed novel features based on distributed word representations, which were learned using deep learning paradigms. Results on test dataset show that our proposed features improve the performance by a margin of 1.9% in terms of F1-score and our team ranks third among 10 teams with 38 systems.

Original languageEnglish
Title of host publicationSemEval 2015 - 9th International Workshop on Semantic Evaluation, co-located with the 2015 Conference of the North American Chapter of the Association for Computational Linguistics
Subtitle of host publicationHuman Language Technologies, NAACL-HLT 2015 - Proceedings
EditorsPreslav Nakov, Torsten Zesch, Daniel Cer, David Jurgens
PublisherAssociation for Computational Linguistics (ACL)
Pages34-39
Number of pages6
ISBN (Electronic)9781941643402
DOIs
StatePublished - 2015
Event9th International Workshop on Semantic Evaluation, SemEval 2015 - Denver, United States
Duration: 4 Jun 20155 Jun 2015

Publication series

NameSemEval 2015 - 9th International Workshop on Semantic Evaluation, co-located with the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2015 - Proceedings

Conference

Conference9th International Workshop on Semantic Evaluation, SemEval 2015
Country/TerritoryUnited States
CityDenver
Period4/06/155/06/15

Fingerprint

Dive into the research topics of 'ECNU: Leveraging Word Embeddings to Boost Performance for Paraphrase in Twitter'. Together they form a unique fingerprint.

Cite this