MITRE at SemEval-2017 Task 1: Simple Semantic Similarity

John Henderson, Elizabeth Merkhofer, Laura Strickhart, Guido Zarrella


Abstract
This paper describes MITRE’s participation in the Semantic Textual Similarity task (SemEval-2017 Task 1), which evaluated machine learning approaches to the identification of similar meaning among text snippets in English, Arabic, Spanish, and Turkish. We detail the techniques we explored ranging from simple bag-of-ngrams classifiers to neural architectures with varied attention and alignment mechanisms. Linear regression is used to tie the systems together into an ensemble submitted for evaluation. The resulting system is capable of matching human similarity ratings of image captions with correlations of 0.73 to 0.83 in monolingual settings and 0.68 to 0.78 in cross-lingual conditions, demonstrating the power of relatively simple approaches.
Anthology ID:
S17-2027
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:
185–190
Language:
URL:
https://aclanthology.org/S17-2027
DOI:
10.18653/v1/S17-2027
Bibkey:
Cite (ACL):
John Henderson, Elizabeth Merkhofer, Laura Strickhart, and Guido Zarrella. 2017. MITRE at SemEval-2017 Task 1: Simple Semantic Similarity. In Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017), pages 185–190, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
MITRE at SemEval-2017 Task 1: Simple Semantic Similarity (Henderson et al., SemEval 2017)
Copy Citation:
PDF:
https://aclanthology.org/S17-2027.pdf
Data
SNLI