Paper Info
Title
Sentence Similarity Based on Contexts
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; (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.
Year
DOI
Venue
2022
10.1162/TACL_A_00477
Transactions of the Association for Computational Linguistics
DocType
Volume
Citations 
Journal
10
0
PageRank 
References 
Authors
0.34
0
7
Name
Order
Citations
PageRank
Xiaofei Sun103.38
Yuxian Meng206.08
Xiang Ao3348.49
Fei Wu42209153.88
Tianwei Zhang502.37
Jiwei Li6102848.05
Chun Fan744.38