@inproceedings{5abd5e2927f04e6b940d731bae7b1ebc,
title = "McPhraSy: Multi-Context Phrase Similarity and Clustering",
abstract = "Phrase similarity is a key component of many NLP applications. Current phrase similarity methods focus on embedding the phrase itself and use the phrase context only during training of the pretrained model. To better leverage the information in the context, we propose McPhraSy (Multi-context Phrase Similarity), a novel algorithm for estimating the similarity of phrases based on multiple contexts. At inference time, McPhraSy represents each phrase by considering multiple contexts in which it appears and computes the similarity of two phrases by aggregating the pairwise similarities between the contexts of the phrases. Incorporating context during inference enables McPhraSy to outperform current state-of-the-art models on two phrase similarity datasets by up to 13.3%. Finally, we also present a new downstream task that relies on phrase similarity - keyphrase clustering - and create a new benchmark for it in the product reviews domain. We show that McPhraSy surpasses all other baselines for this task.",
author = "Cohen, {Amir D.N.} and Hila Gonen and Ori Shapira and Ran Levy and Yoav Goldberg",
note = "Publisher Copyright: {\textcopyright} 2022 Association for Computational Linguistics.; 2022 Findings of the Association for Computational Linguistics: EMNLP 2022 ; Conference date: 07-12-2022 Through 11-12-2022",
year = "2022",
month = jan,
day = "1",
doi = "10.18653/v1/2022.findings-emnlp.431",
language = "American English",
series = "Findings of the Association for Computational Linguistics: EMNLP 2022",
publisher = "Association for Computational Linguistics (ACL)",
pages = "3538--3550",
editor = "Yoav Goldberg and Zornitsa Kozareva and Yue Zhang",
booktitle = "Findings of the Association for Computational Linguistics",
address = "United States",
}