Sentence Similarity Based on Contexts

Xiaofei Sun, Yuxian Meng, Xiang Ao, Fei Wu, Tianwei Zhang, Jiwei Li, Chun Fan


Abstract
Existing methods to measure sentence similarity are faced with two challenges: (1) labeled datasets are usually limited in size, making them insufficient to train supervised neural models; and (2) there is a training-test gap for unsupervised language modeling (LM) based models to compute semantic scores between sentences, since sentence-level semantics are not explicitly modeled at training. This results in inferior performances in this task. In this work, we propose a new framework to address these two issues. The proposed framework is based on the core idea that the meaning of a sentence should be defined by its contexts, and that sentence similarity can be measured by comparing the probabilities of generating two sentences given the same context. The proposed framework is able to generate high-quality, large-scale dataset with semantic similarity scores between two sentences in an unsupervised manner, with which the train-test gap can be largely bridged. Extensive experiments show that the proposed framework achieves significant performance boosts over existing baselines under both the supervised and unsupervised settings across different datasets.
Anthology ID:
2022.tacl-1.33
Volume:
Transactions of the Association for Computational Linguistics, Volume 10
Month:
Year:
2022
Address:
Cambridge, MA
Editors:
Brian Roark, Ani Nenkova
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
573–588
Language:
URL:
https://aclanthology.org/2022.tacl-1.33
DOI:
10.1162/tacl_a_00477
Bibkey:
Cite (ACL):
Xiaofei Sun, Yuxian Meng, Xiang Ao, Fei Wu, Tianwei Zhang, Jiwei Li, and Chun Fan. 2022. Sentence Similarity Based on Contexts. Transactions of the Association for Computational Linguistics, 10:573–588.
Cite (Informal):
Sentence Similarity Based on Contexts (Sun et al., TACL 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-3/2022.tacl-1.33.pdf