Sentence Meta-Embeddings for Unsupervised Semantic Textual Similarity

Nina Poerner, Ulli Waltinger, Hinrich Schütze


Abstract
We address the task of unsupervised Semantic Textual Similarity (STS) by ensembling diverse pre-trained sentence encoders into sentence meta-embeddings. We apply, extend and evaluate different meta-embedding methods from the word embedding literature at the sentence level, including dimensionality reduction (Yin and Schütze, 2016), generalized Canonical Correlation Analysis (Rastogi et al., 2015) and cross-view auto-encoders (Bollegala and Bao, 2018). Our sentence meta-embeddings set a new unsupervised State of The Art (SoTA) on the STS Benchmark and on the STS12-STS16 datasets, with gains of between 3.7% and 6.4% Pearson’s r over single-source systems.
Anthology ID:
2020.acl-main.628
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Editors:
Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7027–7034
Language:
URL:
https://aclanthology.org/2020.acl-main.628
DOI:
10.18653/v1/2020.acl-main.628
Bibkey:
Cite (ACL):
Nina Poerner, Ulli Waltinger, and Hinrich Schütze. 2020. Sentence Meta-Embeddings for Unsupervised Semantic Textual Similarity. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7027–7034, Online. Association for Computational Linguistics.
Cite (Informal):
Sentence Meta-Embeddings for Unsupervised Semantic Textual Similarity (Poerner et al., ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.628.pdf
Video:
 http://slideslive.com/38929064
Data
SentEval