EMNLP Findings2022
McPhraSy: Multi-Context Phrase Similarity and Clustering
Amir David Nissan Cohen, Hila Gonen, Ori Shapira, Ran Levy, Yoav Goldberg
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-theart 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.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- UCTopic: Unsupervised Contrastive Learning for Phrase Representations and Topic Mining cites LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention
- UCTopic: Unsupervised Contrastive Learning for Phrase Representations and Topic Mining cites Phrase-BERT: Improved Phrase Embeddings from BERT with an Application to Corpus Exploration
- Phrase-BERT: Improved Phrase Embeddings from BERT with an Application to Corpus Exploration cites Assessing Phrasal Representation and Composition in Transformers
Cited by top-tier papers1
Builds on6
- LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attentionIkuya Yamada, Akari Asai, Hiroyuki Shindo, Hideaki Takeda et al.EMNLP 2020 · 562 citations
- UCTopic: Unsupervised Contrastive Learning for Phrase Representations and Topic MiningJiacheng Li, Jingbo Shang, Julian J. McAuleyACL 2022 · 68 citations
- Assessing Phrasal Representation and Composition in TransformersLang Yu, Allyson EttingerEMNLP 2020 · 60 citations
- Phrase-BERT: Improved Phrase Embeddings from BERT with an Application to Corpus ExplorationShufan Wang, Laure Thompson, Mohit IyyerEMNLP 2021 · 53 citations
- Extending Multi-Sense Word Embedding to Phrases and Sentences for Unsupervised Semantic ApplicationsHaw-Shiuan Chang, Amol Agrawal, Andrew McCallumAAAI 2021 · 9 citations
Related papers
- MUDY: Multi-Granular Dynamic Candidate Contextualization for Unsupervised Keyphrase ExtractionHyeongu Kang, Susik YoonSIGIR 2026
- Importance Estimation from Multiple Perspectives for Keyphrase ExtractionMingyang Song, Liping Jing, Lin XiaoEMNLP 2021 · 17 citations
- When Phrases Meet Probabilities: Enabling Open Relation Extraction with Cooperating Large Language ModelsJiaxin Wang, Lingling Zhang, Wee Sun Lee, Yujie Zhong et al.ACL 2024
- UCPhrase: Unsupervised Context-aware Quality Phrase TaggingXiaotao Gu, Zihan Wang, Zhenyu Bi, Yu Meng et al.KDD 2021 · 17 citations
- Keyphrase Generation with Fine-Grained Evaluation-Guided Reinforcement LearningYichao Luo, Yige Xu, Jiacheng Ye, Xipeng Qiu et al.EMNLP Findings 2021 · 13 citations
