@inproceedings{wang-yu-2023-going,
    title = "Going Beyond Sentence Embeddings: A Token-Level Matching Algorithm for Calculating Semantic Textual Similarity",
    author = "Wang, Hongwei  and
      Yu, Dong",
    editor = "Rogers, Anna  and
      Boyd-Graber, Jordan  and
      Okazaki, Naoaki",
    booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2023.acl-short.49/",
    doi = "10.18653/v1/2023.acl-short.49",
    pages = "563--570",
    abstract = "Semantic Textual Similarity (STS) measures the degree to which the underlying semantics of paired sentences are equivalent. State-of-the-art methods for STS task use language models to encode sentences into embeddings. However, these embeddings are limited in representing semantics because they mix all the semantic information together in fixed-length vectors, which are difficult to recover and lack explainability. This paper presents a token-level matching inference algorithm, which can be applied on top of any language model to improve its performance on STS task. Our method calculates pairwise token-level similarity and token matching scores, and then aggregates them with pretrained token weights to produce sentence similarity. Experimental results on seven STS datasets show that our method improves the performance of almost all language models, with up to 12.7{\%} gain in Spearman{'}s correlation. We also demonstrate that our method is highly explainable and computationally efficient."
}