ECNU at SemEval-2017 Task 1: Leverage Kernel-based Traditional NLP features and Neural Networks to Build a Universal Model for Multilingual and Cross-lingual Semantic Textual Similarity

  • Junfeng Tian
  • , Zhiheng Zhou
  • , Man Lan*
  • , Yuanbin Wu
  • *Corresponding author for this work

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

68 Scopus citations

Abstract

To model semantic similarity for multilingual and cross-lingual sentence pairs, we first translate foreign languages into English, and then build an efficient monolingual English system with multiple NLP features. Our system is further supported by deep learning models and our best run achieves the mean Pearson correlation 73.16% in primary track.

Original languageEnglish
Title of host publicationACL 2017 - 11th International Workshop on Semantic Evaluations, SemEval 2017, Proceedings of the Workshop
PublisherAssociation for Computational Linguistics (ACL)
Pages191-197
Number of pages7
ISBN (Electronic)9781945626555
DOIs
StatePublished - 2017
Event11th International Workshop on Semantic Evaluations, SemEval 2017, co-located with the 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017 - Vancouver, Canada
Duration: 3 Aug 20174 Aug 2017

Publication series

NameProceedings of the Annual Meeting of the Association for Computational Linguistics
ISSN (Print)0736-587X

Conference

Conference11th International Workshop on Semantic Evaluations, SemEval 2017, co-located with the 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017
Country/TerritoryCanada
CityVancouver
Period3/08/174/08/17

Fingerprint

Dive into the research topics of 'ECNU at SemEval-2017 Task 1: Leverage Kernel-based Traditional NLP features and Neural Networks to Build a Universal Model for Multilingual and Cross-lingual Semantic Textual Similarity'. Together they form a unique fingerprint.

Cite this