mlsanityData to 14 Oct 2026

"What do others think?": Task-Oriented Conversational Modeling with Subjective Knowledge

arXiv 2305.12091 ↗First posted 20 May 2023cs.CLcited by 6

Not on the map. Why?

Abstract (arXiv)

Task-oriented Dialogue (TOD) Systems aim to build dialogue systems that assist users in accomplishing specific goals, such as booking a hotel or a restaurant. Traditional TODs rely on domain-specific APIs/DBs or external factual knowledge to generate responses, which cannot accommodate subjective user requests (e.g., "Is the WIFI reliable?" or "Does the restaurant have a good atmosphere?"). To address this issue, we propose a novel task of subjective-knowledge-based TOD (SK-TOD). We also propose the first corresponding dataset, which contains subjective knowledge-seeking dialogue contexts and manually annotated responses grounded in subjective knowledge sources. When evaluated with existing TOD approaches, we find that this task poses new challenges such as aggregating diverse opinions from multiple knowledge snippets. We hope this task and dataset can promote further research on TOD and subjective content understanding. The code and the dataset are available at https://github.com/alexa/dstc11-track5.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 39 of its 79 references that are in the map. First posted on arXiv 20 May 2023.

Builds on

39 of 79 references.

References · 39

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  5. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  6. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  7. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,790
  8. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,181
  9. 2017Accurate, Large Minibatch SGD: Training ImageNet in 1 Hourcited by 1,492
  10. 2018Hierarchical Neural Story Generationcited by 1,193
  11. 2019DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generationcited by 842
  12. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 766
27 more
  1. 2018Wizard of Wikipedia: Knowledge-Powered Conversational agentscited by 530
  2. 2019Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Datasetcited by 434
  3. 2021Internet-Augmented Dialogue Generationcited by 217
  4. 2019TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agentscited by 188
  5. 2017Key-Value Retrieval Networks for Task-Oriented Dialoguecited by 138
  6. 2017A Knowledge-Grounded Neural Conversation Modelcited by 136
  7. 2018Training Millions of Personalized Dialogue Agentscited by 126
  8. 2018A Dataset for Document Grounded Conversationscited by 104
  9. 2021Aspect Sentiment Quad Prediction as Paraphrase Generationcited by 100
  10. 2020doc2dial: A Goal-Oriented Document-Grounded Dialogue Datasetcited by 88
  11. 2020Extractive Opinion Summarization in Quantized Transformer Spacescited by 76
  12. 2018Interpretation of Natural Language Rules in Conversational Machine Readingcited by 75
  13. 2019Unsupervised Opinion Summarization as Copycat-Review Generationcited by 68
  14. 2019Grounded Conversation Generation as Guided Traverses in Commonsense Knowledge Graphscited by 59
  15. 2020Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Accesscited by 58
  16. 2018Towards Exploiting Background Knowledge for Building Conversation Systemscited by 57
  17. 2021MultiDoc2Dial: Modeling Dialogues Grounded in Multiple Documentscited by 53
  18. 2019Global-to-local Memory Pointer Networks for Task-Oriented Dialoguecited by 47
  19. 2019DyKgChat: Benchmarking Dialogue Generation Grounding on Dynamic Knowledge Graphscited by 33
  20. 2021"How Robust r u?": Evaluating Task-Oriented Dialogue Systems on Spoken Conversationscited by 30
  21. 2015Addressing Complex and Subjective Product-Related Queries with Customer Reviewscited by 29
  22. 2019Introducing MANtIS: a novel Multi-Domain Information Seeking Dialogues Datasetcited by 26
  23. 2020SubjQA: A Dataset for Subjectivity and Review Comprehensioncited by 24
  24. 2022KETOD: Knowledge-Enriched Task-Oriented Dialoguecited by 12
  25. 2019Weakly-Supervised Opinion Summarization by Leveraging External Informationcited by 11
  26. 2021Can I Be of Further Assistance? Using Unstructured Knowledge Access to Improve Task-oriented Conversational Modelingcited by 8
  27. 2022Achieving Conversational Goals with Unsupervised Post-hoc Knowledge Injectioncited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 1; 2025: 1; 2026: 2.

6 papers.

  1. 2023SUQL: Conversational Search over Structured and Unstructured Data with Large Language Modelscited by 13
  2. 2024Should We Fine-Tune or RAG? Evaluating Different Techniques to Adapt LLMs for Dialoguecited by 7
  3. 2025OpinioRAG: Towards Generating User-Centric Opinion Highlights from Large-scale Online Reviewscited by 4
  4. 2023Leveraging Few-Shot Data Augmentation and Waterfall Prompting for Response Generationcited by 1
  5. 2026User Review Writing via Interview with Dialogue Systemscited by 1
  6. 2026Do Audio Language Models Use Paralinguistic Evidence? Counterfactual Audits for Response Evaluationcited by 1