mlsanityData to 7 Oct 2026

DIALKI: Knowledge Identification in Conversational Systems through Dialogue-Document Contextualization

arXiv 2109.04673 ↗First posted 10 Sep 2021cs.CLcited by 21

Not on the map. Why?

Abstract (arXiv)

Identifying relevant knowledge to be used in conversational systems that are grounded in long documents is critical to effective response generation. We introduce a knowledge identification model that leverages the document structure to provide dialogue-contextualized passage encodings and better locate knowledge relevant to the conversation. An auxiliary loss captures the history of dialogue-document connections. We demonstrate the effectiveness of our model on two document-grounded conversational datasets and provide analyses showing generalization to unseen documents and long dialogue contexts.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 30 of its 34 references that are in the map. First posted on arXiv 10 Sep 2021.

Builds on

30 of 34 references.

References · 30

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  6. 2020Longformer: The Long-Document Transformercited by 3,362
  7. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,790
  8. 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 820
  9. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  10. 2018CoQA: A Conversational Question Answering Challengecited by 674
  11. 2019Defending Against Neural Fake Newscited by 553
  12. 2018Wizard of Wikipedia: Knowledge-Powered Conversational agentscited by 530
18 more
  1. 2018QuAC : Question Answering in Contextcited by 379
  2. 2017A Knowledge-Grounded Neural Conversation Modelcited by 136
  3. 2020Knowledge-Grounded Dialogue Generation with Pre-trained Language Modelscited by 107
  4. 2018A Dataset for Document Grounded Conversationscited by 104
  5. 2020Toxicity Detection: Does Context Really Matter?cited by 93
  6. 2020doc2dial: A Goal-Oriented Document-Grounded Dialogue Datasetcited by 88
  7. 2020Sequential Latent Knowledge Selection for Knowledge-Grounded Dialoguecited by 82
  8. 2019Learning to Select Knowledge for Response Generation in Dialog Systemscited by 80
  9. 2018Interpretation of Natural Language Rules in Conversational Machine Readingcited by 72
  10. 2019Knowledge Guided Text Retrieval and Reading for Open Domain Question Answeringcited by 59
  11. 2018Towards Exploiting Background Knowledge for Building Conversation Systemscited by 57
  12. 2016Tracking the World State with Recurrent Entity Networkscited by 51
  13. 2020A Controllable Model of Grounded Response Generationcited by 49
  14. 2019Incremental Transformer with Deliberation Decoder for Document Grounded Conversationscited by 35
  15. 2019DeepCopy: Grounded Response Generation with Hierarchical Pointer Networkscited by 22
  16. 2020Posterior Differential Regularization with f-divergence for Improving Model Robustnesscited by 20
  17. 2020Probabilistic Assumptions Matter: Improved Models for Distantly-Supervised Document-Level Question Answeringcited by 17
  18. 2020Difference-aware Knowledge Selection for Knowledge-grounded Conversation Generationcited by 14

Built on by

Cited by year

Citing papers per year: 2022: 8; 2023: 7; 2024: 6.

21 papers.

Sort:

By area:

  1. 2022State-of-the-art generalisation research in NLP: A taxonomy and reviewcited by 97
  2. 2022In-Context Learning for Few-Shot Dialogue State Trackingcited by 47
  3. 2022INSCIT: Information-Seeking Conversations with Mixed-Initiative Interactionscited by 27
  4. 2023Generative Knowledge Selection for Knowledge-Grounded Dialoguescited by 15
  5. 2022Enhanced Knowledge Selection for Grounded Dialogues via Document Semantic Graphscited by 11
  6. 2023Unleashing Potential of Evidence in Knowledge-Intensive Dialogue Generationcited by 11
  7. 2024LARA: Linguistic-Adaptive Retrieval-Augmentation for Multi-Turn Intent Classificationcited by 10
  8. 2022UniGDD: A Unified Generative Framework for Goal-Oriented Document-Grounded Dialoguecited by 8
  9. 2023PK-ICR: Persona-Knowledge Interactive Context Retrieval for Grounded Dialoguecited by 6
  10. 2022CorefDiffs: Co-referential and Differential Knowledge Flow in Document Grounded Conversationscited by 4
  11. 2023Causal Document-Grounded Dialogue Pre-trainingcited by 4
  12. 2023K-ESConv: Knowledge Injection for Emotional Support Dialogue Systems via Prompt Learningcited by 3
9 more
  1. 2024UniRetriever: Multi-task Candidates Selection for Various Context-Adaptive Conversational Retrievalcited by 3
  2. 2022Building Knowledge-Grounded Dialogue Systems with Graph-Based Semantic Modelingcited by 2
  3. 2022Mind the Knowledge Gap: A Survey of Knowledge-enhanced Dialogue Systemscited by 1
  4. 2023Contextual Knowledge Learning For Dialogue Generationcited by 1
  5. 2023Blending Reward Functions via Few Expert Demonstrations for Faithful and Accurate Knowledge-Grounded Dialogue Generationcited by 0
  6. 2024CET2: Modelling Topic Transitions for Coherent and Engaging Knowledge-Grounded Conversationscited by 0
  7. 2024Bridging Information Gaps in Dialogues With Grounded Exchanges Using Knowledge Graphscited by 0
  8. 2024Structured List-Grounded Question Answeringcited by 0
  9. 2024Policy-driven Knowledge Selection and Response Generation for Document-grounded Dialoguecited by 0