mlsanityData to 13 Oct 2026

Divide and Conquer: Text Semantic Matching with Disentangled Keywords and Intents

arXiv 2203.02898 ↗First posted 6 Mar 2022cs.CLcited by 9

Not on the map. Why?

Abstract (arXiv)

Text semantic matching is a fundamental task that has been widely used in various scenarios, such as community question answering, information retrieval, and recommendation. Most state-of-the-art matching models, e.g., BERT, directly perform text comparison by processing each word uniformly. However, a query sentence generally comprises content that calls for different levels of matching granularity. Specifically, keywords represent factual information such as action, entity, and event that should be strictly matched, while intents convey abstract concepts and ideas that can be paraphrased into various expressions. In this work, we propose a simple yet effective training strategy for text semantic matching in a divide-and-conquer manner by disentangling keywords from intents. Our approach can be easily combined with pre-trained language models (PLM) without influencing their inference efficiency, achieving stable performance improvements against a wide range of PLMs on three benchmarks.

Key facts. Cited by 9 papers in the map (data through 13 Oct 2026). Builds on 34 of its 52 references that are in the map. First posted on arXiv 6 Mar 2022.

Builds on

34 of 52 references.

References · 34

  1. 2017Attention Is All You Needcited by 60,106
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,304
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,322
  4. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,880
  5. 2021On the Opportunities and Risks of Foundation Modelscited by 3,999
  6. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,779
  7. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,171
  8. 2019SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systemscited by 1,725
  9. 2017SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluationcited by 998
  10. 2015Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networkscited by 305
  11. 2020Revisiting Pre-Trained Models for Chinese Natural Language Processingcited by 264
  12. 2016A Decomposable Attention Model for Natural Language Inferencecited by 214
22 more
  1. 2016Enhanced LSTM for Natural Language Inferencecited by 200
  2. 2020Funnel-Transformer: Filtering out Sequential Redundancy for Efficient Language Processingcited by 162
  3. 2016Long Short-Term Memory-Networks for Machine Readingcited by 161
  4. 2017Bilateral Multi-Perspective Matching for Natural Language Sentencescited by 121
  5. 2020BOND: BERT-Assisted Open-Domain Named Entity Recognition with Distant Supervisioncited by 91
  6. 2015Convolutional Neural Network Architectures for Matching Natural Language Sentencescited by 82
  7. 2015Deep Sentence Embedding Using Long Short-Term Memory Networks: Analysis and Application to Information Retrievalcited by 54
  8. 2019Distantly Supervised Named Entity Recognition using Positive-Unlabeled Learningcited by 46
  9. 2018Explicit Bias Discovery in Visual Question Answering Modelscited by 42
  10. 2021Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-Trainingcited by 41
  11. 2017Natural Language Inference over Interaction Spacecited by 34
  12. 2019Decomposable Neural Paraphrase Generationcited by 30
  13. 2020Joint Item Recommendation and Attribute Inference: An Adaptive Graph Convolutional Network Approachcited by 30
  14. 2019Simple and Effective Text Matching with Richer Alignment Featurescited by 29
  15. 2021Using Adversarial Attacks to Reveal the Statistical Bias in Machine Reading Comprehension Modelscited by 29
  16. 2018Semantic Sentence Matching with Densely-connected Recurrent and Co-attentive Informationcited by 28
  17. 2020MultiCQA: Zero-Shot Transfer of Self-Supervised Text Matching Models on a Massive Scalecited by 20
  18. 2016Sentence Similarity Learning by Lexical Decomposition and Compositioncited by 16
  19. 2017Compare, Compress and Propagate: Enhancing Neural Architectures with Alignment Factorization for Natural Language Inferencecited by 10
  20. 2018Co-Stack Residual Affinity Networks with Multi-level Attention Refinement for Matching Text Sequencescited by 10
  21. 2021Match-Ignition: Plugging PageRank into Transformer for Long-form Text Matchingcited by 5
  22. 2020R2-Net: Relation of Relation Learning Network for Sentence Semantic Matchingcited by 4

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2; 2024: 3; 2025: 3.

9 papers.

  1. 2022Disentangled Representation Learningcited by 112
  2. 2024Multi-Intent Attribute-Aware Text Matching in Searchingcited by 4
  3. 2024Explanation based Bias Decoupling Regularization for Natural Language Inferencecited by 3
  4. 2025WDMIR: Wavelet-Driven Multimodal Intent Recognitioncited by 2
  5. 2025Pastiche Novel Generation Creating: Fan Fiction You Love in Your Favorite Author's Stylecited by 1
  6. 2025Highlighting Case Studies in LLM Literature Review of Interdisciplinary System Sciencecited by 1
  7. 2023The Short Text Matching Model Enhanced with Knowledge via Contrastive Learningcited by 0
  8. 2023Inducing Causal Structure for Abstractive Text Summarizationcited by 0
  9. 2024A General and Flexible Multi-concept Parsing Framework for Multilingual Semantic Matchingcited by 0