mlsanityData to 14 Oct 2026

Enhancing Idiomatic Representation in Multiple Languages via an Adaptive Contrastive Triplet Loss

arXiv 2406.15175 ↗First posted 21 Jun 2024cs.CL cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

Accurately modeling idiomatic or non-compositional language has been a longstanding challenge in Natural Language Processing (NLP). This is partly because these expressions do not derive their meanings solely from their constituent words, but also due to the scarcity of relevant data resources, and their impact on the performance of downstream tasks such as machine translation and simplification. In this paper we propose an approach to model idiomaticity effectively using a triplet loss that incorporates the asymmetric contribution of components words to an idiomatic meaning for training language models by using adaptive contrastive learning and resampling miners to build an idiomatic-aware learning objective. Our proposed method is evaluated on a SemEval challenge and outperforms previous alternatives significantly in many metrics.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 38 of its 72 references that are in the map. First posted on arXiv 21 Jun 2024.

Builds on

38 of 72 references.

References · 38

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  5. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  6. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  7. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
  8. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  9. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,918
  10. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,849
  11. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,173
  12. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,253
26 more
  1. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 849
  2. 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 723
  3. 2021Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Modelscited by 463
  4. 2021Large Dual Encoders Are Generalizable Retrieverscited by 456
  5. 2020Circle Loss: A Unified Perspective of Pair Similarity Optimizationcited by 403
  6. 2022Text and Code Embeddings by Contrastive Pre-Trainingcited by 361
  7. 2020DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representationscited by 251
  8. 2020CERT: Contrastive Self-supervised Learning for Language Understandingcited by 169
  9. 2021Contrastive Learning for Many-to-many Multilingual Neural Machine Translationcited by 108
  10. 2021Self-Guided Contrastive Learning for BERT Sentence Representationscited by 103
  11. 2020ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive Learningcited by 72
  12. 2022SemEval-2022 Task 2: Multilingual Idiomaticity Detection and Sentence Embeddingcited by 36
  13. 2019Is a Single Vector Enough? Exploring Node Polysemy for Network Embeddingcited by 29
  14. 2022PCL: Peer-Contrastive Learning with Diverse Augmentations for Unsupervised Sentence Embeddingscited by 29
  15. 2021AStitchInLanguageModels: Dataset and Methods for the Exploration of Idiomaticity in Pre-Trained Language Modelscited by 27
  16. 2021Investigating Robustness of Dialog Models to Popular Figurative Language Constructscited by 19
  17. 2022Improving Tokenisation by Alternative Treatment of Spacescited by 19
  18. 2023SimCSE++: Improving Contrastive Learning for Sentence Embeddings from Two Perspectivescited by 15
  19. 2023Crossing the Threshold: Idiomatic Machine Translation through Retrieval Augmentation and Loss Weightingcited by 11
  20. 2016Adaptive Joint Learning of Compositional and Non-Compositional Phrase Embeddingscited by 9
  21. 2022drsphelps at SemEval-2022 Task 2: Learning idiom representations using BERTRAMcited by 5
  22. 2016Discriminative Phrase Embedding for Paraphrase Identificationcited by 4
  23. 2022Vector Representations of Idioms in Conversational Systemscited by 4
  24. 2023Idioms, Probing and Dangerous Things: Towards Structural Probing for Idiomaticity in Vector Spacecited by 3
  25. 2023Unified Representation for Non-compositional and Compositional Expressionscited by 2
  26. 2023Non-Compositionality in Sentiment: New Data and Analysescited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 3.

7 papers.

  1. 2025SemEval-2025 Task 1: AdMIRe -- Advancing Multimodal Idiomaticity Representationcited by 3
  2. 2025UoR-NCL at SemEval-2025 Task 1: Using Generative LLMs and CLIP Models for Multilingual Multimodal Idiomaticity Representationcited by 2
  3. 2025NLP Datasets for Idiom and Figurative Language Taskscited by 2
  4. 2025From Input Perception to Predictive Insight: Modeling Model Blind Spots Before They Become Errorscited by 1
  5. 2026A Rising Tide Lifts All Boats: MTQE Rewards for Idioms Improve General Translation Qualitycited by 1
  6. 2026Span Modeling for Idiomaticity and Figurative Language Detection with Span Contrastive Losscited by 0
  7. 2026IdioLink: Retrieving Meaning Beyond Words Across Idiomatic and Literal Expressionscited by 0