SimBow at SemEval-2017 Task 3: Soft-Cosine Semantic Similarity between Questions for Community Question Answering

Delphine Charlet, Géraldine Damnati


Abstract
This paper describes the SimBow system submitted at SemEval2017-Task3, for the question-question similarity subtask B. The proposed approach is a supervised combination of different unsupervised textual similarities. These textual similarities rely on the introduction of a relation matrix in the classical cosine similarity between bag-of-words, so as to get a soft-cosine that takes into account relations between words. According to the type of relation matrix embedded in the soft-cosine, semantic or lexical relations can be considered. Our system ranked first among the official submissions of subtask B.
Anthology ID:
S17-2051
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:
315–319
Language:
URL:
https://aclanthology.org/S17-2051
DOI:
10.18653/v1/S17-2051
Bibkey:
Cite (ACL):
Delphine Charlet and Géraldine Damnati. 2017. SimBow at SemEval-2017 Task 3: Soft-Cosine Semantic Similarity between Questions for Community Question Answering. In Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017), pages 315–319, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
SimBow at SemEval-2017 Task 3: Soft-Cosine Semantic Similarity between Questions for Community Question Answering (Charlet & Damnati, SemEval 2017)
Copy Citation:
PDF:
https://aclanthology.org/S17-2051.pdf