Unsupervised Sentence Textual Similarity with Compositional Phrase Semantics. (arXiv:2210.02284v1 [cs.CL])

Measuring Sentence Textual Similarity (STS) is a classic task that can be
applied to many downstream NLP applications such as text generation and
retrieval. In this paper, we focus on unsupervised STS that works on various
domains but only requires minimal data and computational resources.
Theoretically, we propose a light-weighted Expectation-Correction (EC)
formulation for STS computation. EC formulation unifies unsupervised STS
approaches including the cosine similarity of Additively Composed (AC) sentence
embeddings, Optimal Transport (OT), and Tree Kernels (TK). Moreover, …

arxiv semantics unsupervised