mlsanityData to 7 Oct 2026

EASE: Entity-Aware Contrastive Learning of Sentence Embedding

arXiv 2205.04260 ↗First posted 9 May 2022cs.CLcited by 21

Not on the map. Why?

Abstract (arXiv)

We present EASE, a novel method for learning sentence embeddings via contrastive learning between sentences and their related entities. The advantage of using entity supervision is twofold: (1) entities have been shown to be a strong indicator of text semantics and thus should provide rich training signals for sentence embeddings; (2) entities are defined independently of languages and thus offer useful cross-lingual alignment supervision. We evaluate EASE against other unsupervised models both in monolingual and multilingual settings. We show that EASE exhibits competitive or better performance in English semantic textual similarity (STS) and short text clustering (STC) tasks and it significantly outperforms baseline methods in multilingual settings on a variety of tasks. Our source code, pre-trained models, and newly constructed multilingual STC dataset are available at https://github.com/studio-ousia/ease.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 35 of its 62 references that are in the map. First posted on arXiv 9 May 2022.

Builds on

35 of 62 references.

References · 35

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  5. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  6. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
  7. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,393
  8. 2017SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluationcited by 998
  9. 2020XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalizationcited by 738
  10. 2014Distributed Representations of Sentences and Documentscited by 677
  11. 2020Language-agnostic BERT Sentence Embeddingcited by 621
  12. 2020Contrastive Learning with Hard Negative Samplescited by 619
23 more
  1. 2020Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillationcited by 591
  2. 2018Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyondcited by 434
  3. 2017Supervised Learning of Universal Sentence Representations from Natural Language Inference Datacited by 428
  4. 2015Skip-Thought Vectorscited by 321
  5. 2020DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representationscited by 249
  6. 2021ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfercited by 231
  7. 2018An efficient framework for learning sentence representationscited by 197
  8. 2020CERT: Contrastive Self-supervised Learning for Language Understandingcited by 169
  9. 2021COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretrainingcited by 126
  10. 2021Self-Guided Contrastive Learning for BERT Sentence Representationscited by 103
  11. 2019Pretrained Encyclopedia: Weakly Supervised Knowledge-Pretrained Language Modelcited by 102
  12. 2021Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoderscited by 88
  13. 2017Learning Joint Multilingual Sentence Representations with Neural Machine Translationcited by 52
  14. 2018A Corpus for Multilingual Document Classification in Eight Languagescited by 42
  15. 2020Universal Sentence Representation Learning with Conditional Masked Language Modelcited by 34
  16. 2021Pairwise Supervised Contrastive Learning of Sentence Representationscited by 31
  17. 2021mLUKE: The Power of Entity Representations in Multilingual Pretrained Language Modelscited by 19
  18. 2021XLM-K: Improving Cross-Lingual Language Model Pre-training with Multilingual Knowledgecited by 18
  19. 2020Learning Cross-Context Entity Representations from Textcited by 12
  20. 2017Learning Distributed Representations of Texts and Entities from Knowledge Basecited by 10
  21. 2021Unsupervised Multilingual Sentence Embeddings for Parallel Corpus Miningcited by 9
  22. 2018Representation Learning of Entities and Documents from Knowledge Base Descriptionscited by 5
  23. 2021A Multilingual Bag-of-Entities Model for Zero-Shot Cross-Lingual Text Classificationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 9; 2024: 5; 2025: 1; 2026: 3.

21 papers.

Sort:

By area:

  1. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  2. 2024When Large Language Models Meet Vector Databases: A Surveycited by 39
  3. 2024Grounding Language Model with Chunking-Free In-Context Retrievalcited by 30
  4. 2024Mix-of-Granularity: Optimize the Chunking Granularity for Retrieval-Augmented Generationcited by 23
  5. 2023Composition-contrastive Learning for Sentence Embeddingscited by 14
  6. 2023A Comprehensive Survey of Sentence Representations: From the BERT Epoch to the ChatGPT Era and Beyondcited by 11
  7. 2023Efficient Domain Adaptation of Sentence Embeddings Using Adapterscited by 6
  8. 2024Assessing News Thumbnail Representativeness: Counterfactual text can enhance the cross-modal matching abilitycited by 3
  9. 2025On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Surveycited by 3
  10. 2022Dial2vec: Self-Guided Contrastive Learning of Unsupervised Dialogue Embeddingscited by 2
  11. 2026MIPIC: Matryoshka Representation Learning via Self-Distilled Intra-Relational and Progressive Information Chainingcited by 2
  12. 2022Analysis of Utterance Embeddings and Clustering Methods Related to Intent Induction for Task-Oriented Dialoguecited by 1
9 more
  1. 2023ESCL: Equivariant Self-Contrastive Learning for Sentence Representationscited by 1
  2. 2023Adapting Sentence Transformers for the Aviation Domaincited by 1
  3. 2023Template-assisted Contrastive Learning of Task-oriented Dialogue Sentence Embeddingscited by 1
  4. 2024SKETCH: Structured Knowledge Enhanced Text Comprehension for Holistic Retrievalcited by 1
  5. 2026MIC: Maximizing Informational Capacity in Adaptive Representations via Isotropic Subspace Alignmentcited by 1
  6. 2022MED-SE: Medical Entity Definition-based Sentence Embeddingcited by 0
  7. 2023KEPLET: Knowledge-Enhanced Pretrained Language Model with Topic Entity Awarenesscited by 0
  8. 2023Semi-supervised News Discourse Profiling with Contrastive Learningcited by 0
  9. 2026JFinTEB: Japanese Financial Text Embedding Benchmarkcited by 0