mlsanityData to 7 Oct 2026

Facilitating Contrastive Learning of Discourse Relational Senses by Exploiting the Hierarchy of Sense Relations

arXiv 2301.02724 ↗First posted 6 Jan 2023cs.CL cs.AIcited by 22

Not on the map. Why?

Abstract (arXiv)

Implicit discourse relation recognition is a challenging task that involves identifying the sense or senses that hold between two adjacent spans of text, in the absence of an explicit connective between them. In both PDTB-2 and PDTB-3, discourse relational senses are organized into a three-level hierarchy ranging from four broad top-level senses, to more specific senses below them. Most previous work on implicit discourse relation recognition have used the sense hierarchy simply to indicate what sense labels were available. Here we do more -- incorporating the sense hierarchy into the recognition process itself and using it to select the negative examples used in contrastive learning. With no additional effort, the approach achieves state-of-the-art performance on the task.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 29 of its 63 references that are in the map. First posted on arXiv 6 Jan 2023.

Builds on

29 of 63 references.

References · 29

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  5. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  6. 2020Supervised Contrastive Learningcited by 2,803
  7. 2018Deep contextualized word representationscited by 2,285
  8. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
  9. 2020Contrastive Learning with Hard Negative Samplescited by 619
  10. 2018A Discourse-Aware Attention Model for Abstractive Summarization of Long Documentscited by 477
  11. 2018Generating Natural Language Adversarial Examplescited by 422
  12. 2020Supervised Contrastive Learning for Pre-trained Language Model Fine-tuningcited by 275
17 more
  1. 2021ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfercited by 231
  2. 2020CLEAR: Contrastive Learning for Sentence Representationcited by 186
  3. 2021Self-Guided Contrastive Learning for BERT Sentence Representationscited by 103
  4. 2021CLINE: Contrastive Learning with Semantic Negative Examples for Natural Language Understandingcited by 50
  5. 2021Not All Negatives are Equal: Label-Aware Contrastive Loss for Fine-grained Text Classificationcited by 43
  6. 2020On the Importance of Word and Sentence Representation Learning in Implicit Discourse Relation Classificationcited by 40
  7. 2021Pairwise Supervised Contrastive Learning of Sentence Representationscited by 31
  8. 2022Exploring the Impact of Negative Samples of Contrastive Learning: A Case Study of Sentence Embeddingcited by 25
  9. 2018Deep Enhanced Representation for Implicit Discourse Relation Recognitioncited by 21
  10. 2021A Label Dependence-aware Sequence Generation Model for Multi-level Implicit Discourse Relation Recognitioncited by 18
  11. 2017Adversarial Connective-exploiting Networks for Implicit Discourse Relation Classificationcited by 17
  12. 2018Improving Implicit Discourse Relation Classification by Modeling Inter-dependencies of Discourse Units in a Paragraphcited by 17
  13. 2016Recognizing Implicit Discourse Relations via Repeated Reading: Neural Networks with Multi-Level Attentioncited by 16
  14. 2018Learning to Explicitate Connectives with Seq2Seq Network for Implicit Discourse Relation Classificationcited by 16
  15. 2021From Discourse to Narrative: Knowledge Projection for Event Relation Extractioncited by 14
  16. 2021Efficient Contrastive Learning via Novel Data Augmentation and Curriculum Learningcited by 14
  17. 2020Extending Implicit Discourse Relation Recognition to the PDTB-3cited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 7; 2024: 6; 2025: 8; 2026: 1.

22 papers.

Sort:

By area:

  1. 2023ChatGPT Evaluation on Sentence Level Relations: A Focus on Temporal, Causal, and Discourse Relationscited by 39
  2. 2023DiscoPrompt: Path Prediction Prompt Tuning for Implicit Discourse Relation Recognitioncited by 23
  3. 2023Annotation-Inspired Implicit Discourse Relation Classification with Auxiliary Discourse Connective Generationcited by 12
  4. 2024Multi-Label Classification for Implicit Discourse Relation Recognitioncited by 9
  5. 2025The Box is in the Pen: Evaluating Commonsense Reasoning in Neural Machine Translationcited by 5
  6. 2023A Novel Computational and Modeling Foundation for Automatic Coherence Assessmentcited by 4
  7. 2023Instances and Labels: Hierarchy-aware Joint Supervised Contrastive Learning for Hierarchical Multi-Label Text Classificationcited by 4
  8. 2024What Causes the Failure of Explicit to Implicit Discourse Relation Recognition?cited by 4
  9. 2024A Multi-Task and Multi-Label Classification Model for Implicit Discourse Relation Recognitioncited by 4
  10. 2023BUCA: A Binary Classification Approach to Unsupervised Commonsense Question Answeringcited by 3
  11. 2024Learning Label Hierarchy with Supervised Contrastive Learningcited by 3
  12. 2023Prompt-based Logical Semantics Enhancement for Implicit Discourse Relation Recognitioncited by 1
10 more
  1. 2024Constrained Multi-Layer Contrastive Learning for Implicit Discourse Relationship Recognitioncited by 1
  2. 2025Tgea: An error-annotated dataset and benchmark tasks for text generation from pretrained language modelscited by 1
  3. 2025Fine-Grained Evaluation for Implicit Discourse Relation Recognitioncited by 1
  4. 2025Evaluating Discourse Cohesion in Pre-trained Language Modelscited by 1
  5. 2025Multi-Lingual Implicit Discourse Relation Recognition with Multi-Label Hierarchical Learningcited by 1
  6. 2025On the Role of Context for Discourse Relation Classification in Scientific Writingcited by 1
  7. 2024Meta-RTL: Reinforcement-Based Meta-Transfer Learning for Low-Resource Commonsense Reasoningcited by 0
  8. 2025Similarity-Based Domain Adaptation with LLMscited by 0
  9. 2025MetaXCR: Reinforcement-Based Meta-Transfer Learning for Cross-Lingual Commonsense Reasoningcited by 0
  10. 2026Improving Implicit Discourse Relation Recognition with Natural Language Explanations from LLMscited by 0