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


Abstract
To address semantic similarity on multilingual and cross-lingual sentences, we firstly translate other foreign languages into English, and then feed our monolingual English system with various interactive features. Our system is further supported by combining with deep learning semantic similarity and our best run achieves the mean Pearson correlation 73.16% in primary track.
Anthology ID:
S17-2028
Volume:
Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)
Month:
August
Year:
2017
Address:
Vancouver, Canada
Editors:
Steven Bethard, Marine Carpuat, Marianna Apidianaki, Saif M. Mohammad, Daniel Cer, David Jurgens
Venue:
SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
191–197
Language:
URL:
https://aclanthology.org/S17-2028
DOI:
10.18653/v1/S17-2028
Bibkey:
Cite (ACL):
Junfeng Tian, Zhiheng Zhou, Man Lan, and Yuanbin Wu. 2017. 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. In Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017), pages 191–197, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
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 (Tian et al., SemEval 2017)
Copy Citation:
PDF:
https://aclanthology.org/S17-2028.pdf