STS-UHH at SemEval-2017 Task 1: Scoring Semantic Textual Similarity Using Supervised and Unsupervised Ensemble

Sarah Kohail, Amr Rekaby Salama, Chris Biemann


Abstract
This paper reports the STS-UHH participation in the SemEval 2017 shared Task 1 of Semantic Textual Similarity (STS). Overall, we submitted 3 runs covering monolingual and cross-lingual STS tracks. Our participation involves two approaches: unsupervised approach, which estimates a word alignment-based similarity score, and supervised approach, which combines dependency graph similarity and coverage features with lexical similarity measures using regression methods. We also present a way on ensembling both models. Out of 84 submitted runs, our team best multi-lingual run has been ranked 12th in overall performance with correlation of 0.61, 7th among 31 participating teams.
Anthology ID:
S17-2025
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:
175–179
Language:
URL:
https://aclanthology.org/S17-2025
DOI:
10.18653/v1/S17-2025
Bibkey:
Cite (ACL):
Sarah Kohail, Amr Rekaby Salama, and Chris Biemann. 2017. STS-UHH at SemEval-2017 Task 1: Scoring Semantic Textual Similarity Using Supervised and Unsupervised Ensemble. In Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017), pages 175–179, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
STS-UHH at SemEval-2017 Task 1: Scoring Semantic Textual Similarity Using Supervised and Unsupervised Ensemble (Kohail et al., SemEval 2017)
Copy Citation:
PDF:
https://aclanthology.org/S17-2025.pdf