mlsanityData to 7 Oct 2026

Semantic-aware Contrastive Learning for More Accurate Semantic Parsing

arXiv 2301.07919 ↗First posted 19 Jan 2023cs.CLcited by 2

Not on the map. Why?

Abstract (arXiv)

Since the meaning representations are detailed and accurate annotations which express fine-grained sequence-level semtantics, it is usually hard to train discriminative semantic parsers via Maximum Likelihood Estimation (MLE) in an autoregressive fashion. In this paper, we propose a semantic-aware contrastive learning algorithm, which can learn to distinguish fine-grained meaning representations and take the overall sequence-level semantic into consideration. Specifically, a multi-level online sampling algorithm is proposed to sample confusing and diverse instances. Three semantic-aware similarity functions are designed to accurately measure the distance between meaning representations as a whole. And a ranked contrastive loss is proposed to pull the representations of the semantic-identical instances together and push negative instances away. Experiments on two standard datasets show that our approach achieves significant improvements over MLE baselines and gets state-of-the-art performances by simply applying semantic-aware contrastive learning on a vanilla Seq2Seq model.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 40 of its 56 references that are in the map. First posted on arXiv 19 Jan 2023.

Builds on

40 of 56 references.

References · 40

  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. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  6. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
  7. 2020DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representationscited by 249
  8. 2019Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representationcited by 210
  9. 2021Constrained Language Models Yield Few-Shot Semantic Parserscited by 162
  10. 2016Language to Logical Form with Neural Attentioncited by 158
  11. 2016Dual Learning for Machine Translationcited by 146
  12. 2015Minimum Risk Training for Neural Machine Translationcited by 114
28 more
  1. 2016Data Recombination for Neural Semantic Parsingcited by 111
  2. 2021Self-Guided Contrastive Learning for BERT Sentence Representationscited by 103
  3. 2017Abstract Syntax Networks for Code Generation and Semantic Parsingcited by 92
  4. 2020ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive Learningcited by 72
  5. 2021Meta-Learning to Compositionally Generalizecited by 62
  6. 2017Paraphrase Generation with Deep Reinforcement Learningcited by 58
  7. 2020Contrastive Learning with Adversarial Perturbations for Conditional Text Generationcited by 56
  8. 2021Unlocking Compositional Generalization in Pre-trained Models Using Intermediate Representationscited by 55
  9. 2020Compositional Generalization by Learning Analytical Expressionscited by 53
  10. 2021CLINE: Contrastive Learning with Semantic Negative Examples for Natural Language Understandingcited by 50
  11. 2017Learning to Paraphrase for Question Answeringcited by 46
  12. 2020Improving Compositional Generalization in Semantic Parsingcited by 42
  13. 2017From Language to Programs: Bridging Reinforcement Learning and Maximum Marginal Likelihoodcited by 41
  14. 2020CoDA: Contrast-enhanced and Diversity-promoting Data Augmentation for Natural Language Understandingcited by 41
  15. 2021CLEVE: Contrastive Pre-training for Event Extractioncited by 36
  16. 2019Semantic Parsing with Dual Learningcited by 28
  17. 2019Don't paraphrase, detect! Rapid and Effective Data Collection for Semantic Parsingcited by 24
  18. 2018StructVAE: Tree-structured Latent Variable Models for Semi-supervised Semantic Parsingcited by 22
  19. 2018Sequence-to-Action: End-to-End Semantic Graph Generation for Semantic Parsingcited by 21
  20. 2020Unsupervised Dual Paraphrasing for Two-stage Semantic Parsingcited by 20
  21. 2017Cross-domain Semantic Parsing via Paraphrasingcited by 19
  22. 2020Unnatural Language Processing: Bridging the Gap Between Synthetic and Natural Language Datacited by 16
  23. 2020Latent Compositional Representations Improve Systematic Generalization in Grounded Question Answeringcited by 16
  24. 2021From Paraphrasing to Semantic Parsing: Unsupervised Semantic Parsing via Synchronous Semantic Decodingcited by 14
  25. 2017Weakly-supervised Semantic Parsing with Abstract Examplescited by 13
  26. 2021CIL: Contrastive Instance Learning Framework for Distantly Supervised Relation Extractioncited by 13
  27. 2021Unsupervised Representation Learning from Pathology Images with Multi-directional Contrastive Predictive Codingcited by 3
  28. 2021A Globally Normalized Neural Model for Semantic Parsingcited by 2

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025From Misleading Queries to Accurate Answers: A Three-Stage Fine-Tuning Method for LLMscited by 2
  2. 20252K-Characters-10K-Stories: A Quality-Gated Stylized Narrative Dataset with Disentangled Control and Sequence Consistencycited by 0