mlsanityData to 7 Oct 2026

Conversational Semantic Role Labeling

arXiv 2104.04947 ↗First posted 11 Apr 2021cs.CL cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

Semantic role labeling (SRL) aims to extract the arguments for each predicate in an input sentence. Traditional SRL can fail to analyze dialogues because it only works on every single sentence, while ellipsis and anaphora frequently occur in dialogues. To address this problem, we propose the conversational SRL task, where an argument can be the dialogue participants, a phrase in the dialogue history or the current sentence. As the existing SRL datasets are in the sentence level, we manually annotate semantic roles for 3,000 chit-chat dialogues (27,198 sentences) to boost the research in this direction. Experiments show that while traditional SRL systems (even with the help of coreference resolution or rewriting) perform poorly for analyzing dialogues, modeling dialogue histories and participants greatly helps the performance, indicating that adapting SRL to conversations is very promising for universal dialogue understanding. Our initial study by applying CSRL to two mainstream conversational tasks, dialogue response generation and dialogue context rewriting, also confirms the usefulness of CSRL.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 34 of its 46 references that are in the map. First posted on arXiv 11 Apr 2021.

Builds on

34 of 46 references.

References · 34

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,281
  5. 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,068
  6. 2015Pointer Networkscited by 882
  7. 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 820
  8. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 760
  9. 2018CoQA: A Conversational Question Answering Challengecited by 674
  10. 2019Unified Language Model Pre-training for Natural Language Understanding and Generationcited by 668
  11. 2017DailyDialog: A Manually Labelled Multi-turn Dialogue Datasetcited by 649
  12. 2018Wizard of Wikipedia: Knowledge-Powered Conversational agentscited by 530
22 more
  1. 2018QuAC : Question Answering in Contextcited by 379
  2. 2018AllenNLP: A Deep Semantic Natural Language Processing Platformcited by 347
  3. 2016A Network-based End-to-End Trainable Task-oriented Dialogue Systemcited by 252
  4. 2017Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoderscited by 222
  5. 2015Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Modelscited by 207
  6. 2015A Neural Conversational Modelcited by 195
  7. 2019TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agentscited by 188
  8. 2016A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialoguescited by 174
  9. 2019Simple BERT Models for Relation Extraction and Semantic Role Labelingcited by 154
  10. 2016Neural Belief Tracker: Data-Driven Dialogue State Trackingcited by 142
  11. 2019BERT for Coreference Resolution: Baselines and Analysiscited by 125
  12. 2015A Neural Network Approach to Context-Sensitive Generation of Conversational Responsescited by 98
  13. 2019Proactive Human-Machine Conversation with Explicit Conversation Goalscited by 87
  14. 2019Personalized Dialogue Generation with Diversified Traitscited by 73
  15. 2020KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven Conversationcited by 59
  16. 2019Improving Multi-turn Dialogue Modelling with Utterance ReWritercited by 57
  17. 2017Generating High-Quality and Informative Conversation Responses with Sequence-to-Sequence Modelscited by 42
  18. 2018Exploiting Semantics in Neural Machine Translation with Graph Convolutional Networkscited by 30
  19. 2017Deep Semantic Role Labeling with Self-Attentioncited by 23
  20. 2019Dependency or Span, End-to-End Uniform Semantic Role Labelingcited by 22
  21. 2018A Span Selection Model for Semantic Role Labelingcited by 15
  22. 2019Consistent Dialogue Generation with Self-supervised Feature Learningcited by 7

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 3; 2023: 2; 2024: 0; 2025: 1.

8 papers.

  1. 2022Conversational Semantic Role Labeling with Predicate-Oriented Latent Graphcited by 14
  2. 2021Domain-Adaptive Pretraining Methods for Dialogue Understandingcited by 11
  3. 2021CSAGN: Conversational Structure Aware Graph Network for Conversational Semantic Role Labelingcited by 5
  4. 2023Evaluating Factual Consistency of Texts with Semantic Role Labelingcited by 4
  5. 2022Learning Locality and Isotropy in Dialogue Modelingcited by 1
  6. 2022Zero-shot Cross-lingual Conversational Semantic Role Labelingcited by 0
  7. 2023Friend-training: Learning from Models of Different but Related Taskscited by 0
  8. 2025RSMLP: A light Sampled MLP Structure for Incomplete Utterance Rewritecited by 0