mlsanityData to 14 Oct 2026

Semantic Representation for Dialogue Modeling

arXiv 2105.10188 ↗First posted 21 May 2021cs.CLcited by 24

Not on the map. Why?

Abstract (arXiv)

Although neural models have achieved competitive results in dialogue systems, they have shown limited ability in representing core semantics, such as ignoring important entities. To this end, we exploit Abstract Meaning Representation (AMR) to help dialogue modeling. Compared with the textual input, AMR explicitly provides core semantic knowledge and reduces data sparsity. We develop an algorithm to construct dialogue-level AMR graphs from sentence-level AMRs and explore two ways to incorporate AMRs into dialogue systems. Experimental results on both dialogue understanding and response generation tasks show the superiority of our model. To our knowledge, we are the first to leverage a formal semantic representation into neural dialogue modeling.

Key facts. Cited by 24 papers in the map (data through 14 Oct 2026). Builds on 49 of its 71 references that are in the map. First posted on arXiv 21 May 2021.

Builds on

49 of 71 references.

References · 49

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2016Layer Normalizationcited by 5,669
  4. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  5. 2014Sequence to Sequence Learning with Neural Networkscited by 2,986
  6. 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,077
  7. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 766
  8. 2018CoQA: A Conversational Question Answering Challengecited by 683
  9. 2017DailyDialog: A Manually Labelled Multi-turn Dialogue Datasetcited by 652
  10. 2018Wizard of Wikipedia: Knowledge-Powered Conversational agentscited by 530
  11. 2019Learning the Difference that Makes a Difference with Counterfactually-Augmented Datacited by 439
  12. 2018QuAC : Question Answering in Contextcited by 381
37 more
  1. 2018Hypothesis Only Baselines in Natural Language Inferencecited by 295
  2. 2016A Network-based End-to-End Trainable Task-oriented Dialogue Systemcited by 252
  3. 2015A Neural Conversational Modelcited by 196
  4. 2016A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialoguescited by 174
  5. 2019PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variablecited by 145
  6. 2015Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systemscited by 134
  7. 2018Semantic Parsing for Task Oriented Dialog using Hierarchical Representationscited by 101
  8. 2020Reasoning with Latent Structure Refinement for Document-Level Relation Extractioncited by 97
  9. 2019Attention Guided Graph Convolutional Networks for Relation Extractioncited by 82
  10. 2018Linguistically-Informed Self-Attention for Semantic Role Labelingcited by 71
  11. 2020Dialogue-Based Relation Extractioncited by 68
  12. 2017Neural AMR: Sequence-to-Sequence Models for Parsing and Generationcited by 56
  13. 2018A Graph-to-Sequence Model for AMR-to-Text Generationcited by 56
  14. 2019AMR Parsing as Sequence-to-Graph Transductioncited by 50
  15. 2020Do Syntax Trees Help Pre-trained Transformers Extract Information?cited by 48
  16. 2020AMR Parsing via Graph-Sequence Iterative Inferencecited by 47
  17. 2017Doubly-Attentive Decoder for Multi-modal Neural Machine Translationcited by 46
  18. 2018Toward Abstractive Summarization Using Semantic Representationscited by 43
  19. 2020Conversational Semantic Parsing for Dialog State Trackingcited by 40
  20. 2019Semantic Neural Machine Translation using AMRcited by 37
  21. 2018AMR Parsing as Graph Prediction with Latent Alignmentcited by 36
  22. 2018Abstract Meaning Representation for Multi-Document Summarizationcited by 35
  23. 2019Modeling Graph Structure in Transformer for Better AMR-to-Text Generationcited by 35
  24. 2019GECOR: An End-to-End Generative Ellipsis and Co-reference Resolution Model for Task-Oriented Dialoguecited by 33
  25. 2018Exploiting Semantics in Neural Machine Translation with Graph Convolutional Networkscited by 30
  26. 2019Implicit Deep Latent Variable Models for Text Generationcited by 26
  27. 2020Improving BERT with Syntax-aware Local Attentioncited by 26
  28. 2018Guided Neural Language Generation for Abstractive Summarization using Abstract Meaning Representationcited by 24
  29. 2021Structural Information Preserving for Graph-to-Text Generationcited by 24
  30. 2019Scaling Multi-Domain Dialogue State Tracking via Query Reformulationcited by 20
  31. 2019Improving Robustness of Task Oriented Dialog Systemscited by 15
  32. 2020Dialogue Relation Extraction with Document-level Heterogeneous Graph Attention Networkscited by 12
  33. 2019Leveraging Dependency Forest for Neural Medical Relation Extractioncited by 10
  34. 2020Online Back-Parsing for AMR-to-Text Generationcited by 9
  35. 2019Improving Dialogue State Tracking by Discerning the Relevant Contextcited by 2
  36. 2018Improving Robustness of Neural Dialog Systems in a Data-Efficient Way with Turn Dropoutcited by 1
  37. 2020AvgOut: A Simple Output-Probability Measure to Eliminate Dull Responsescited by 1

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 11; 2023: 4; 2024: 4; 2025: 2.

24 papers.

Sort:

By area:

  1. 2022Graph Pre-training for AMR Parsing and Generationcited by 55
  2. 2024Don't Forget to Connect! Improving RAG with Graph-based Rerankingcited by 49
  3. 2021Uncovering Main Causalities for Long-tailed Information Extractioncited by 21
  4. 2022Exploiting Sentiment and Common Sense for Zero-shot Stance Detectioncited by 16
  5. 2022Relation Extraction as Open-book Examination: Retrieval-enhanced Prompt Tuningcited by 13
  6. 2021DocAMR: Multi-Sentence AMR Representation and Evaluationcited by 12
  7. 2023Improving Medical Dialogue Generation with Abstract Meaning Representationscited by 10
  8. 2022ThingTalk: An Extensible, Executable Representation Language for Task-Oriented Dialoguescited by 6
  9. 2022GRASP: Guiding model with RelAtional Semantics using Prompt for Dialogue Relation Extractioncited by 4
  10. 2022Unsupervised Syntactically Controlled Paraphrase Generation with Abstract Meaning Representationscited by 4
  11. 2023Linguistic representations for fewer-shot relation extraction across domainscited by 4
  12. 2022Dialogue Meaning Representation for Task-Oriented Dialogue Systemscited by 3
12 more
  1. 2022Semantic-based Pre-training for Dialogue Understandingcited by 3
  2. 2022Cross-domain Generalization for AMR Parsingcited by 2
  3. 2023Exploiting Abstract Meaning Representation for Open-Domain Question Answeringcited by 2
  4. 2024Emphasising Structured Information: Integrating Abstract Meaning Representation into LLMs for Enhanced Open-Domain Dialogue Evaluationcited by 2
  5. 2025Survey of Abstract Meaning Representation: Then, Now, Futurecited by 2
  6. 2021Speaker-Oriented Latent Structures for Dialogue-Based Relation Extractioncited by 1
  7. 2022Mind the Knowledge Gap: A Survey of Knowledge-enhanced Dialogue Systemscited by 1
  8. 2024Adapting Abstract Meaning Representation Parsing to the Clinical Narrative -- the SPRING THYME parsercited by 1
  9. 2022Question-Interlocutor Scope Realized Graph Modeling over Key Utterances for Dialogue Reading Comprehensioncited by 0
  10. 2023Guiding AMR Parsing with Reverse Graph Linearizationcited by 0
  11. 2024X-AMR Annotation Toolcited by 0
  12. 2025Planning with Diffusion Models for Target-Oriented Dialogue Systemscited by 0