mlsanityData to 7 Oct 2026

Learning to Select External Knowledge with Multi-Scale Negative Sampling

arXiv 2102.02096 ↗First posted 3 Feb 2021cs.CLcited by 16

Not on the map. Why?

Abstract (arXiv)

The Track-1 of DSTC9 aims to effectively answer user requests or questions during task-oriented dialogues, which are out of the scope of APIs/DB. By leveraging external knowledge resources, relevant information can be retrieved and encoded into the response generation for these out-of-API-coverage queries. In this work, we have explored several advanced techniques to enhance the utilization of external knowledge and boost the quality of response generation, including schema guided knowledge decision, negatives enhanced knowledge selection, and knowledge grounded response generation. To evaluate the performance of our proposed method, comprehensive experiments have been carried out on the publicly available dataset. Our approach was ranked as the best in human evaluation of DSTC9 Track-1.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 20 of its 32 references that are in the map. First posted on arXiv 3 Feb 2021.

Builds on

20 of 32 references.

References · 20

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  3. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
  4. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  5. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,772
  6. 2018Wizard of Wikipedia: Knowledge-Powered Conversational agentscited by 530
  7. 2016A Network-based End-to-End Trainable Task-oriented Dialogue Systemcited by 252
  8. 2017Efficient Natural Language Response Suggestion for Smart Replycited by 228
  9. 2017Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoderscited by 222
  10. 2020MultiWOZ 2.2 : A Dialogue Dataset with Additional Annotation Corrections and State Tracking Baselinescited by 201
  11. 2019PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variablecited by 145
  12. 2015Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systemscited by 134
8 more
  1. 2020Sequential Latent Knowledge Selection for Knowledge-Grounded Dialoguecited by 82
  2. 2019Learning to Select Knowledge for Response Generation in Dialog Systemscited by 80
  3. 2020PLATO-2: Towards Building an Open-Domain Chatbot via Curriculum Learningcited by 79
  4. 2020Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Accesscited by 58
  5. 2020Augmenting Transformers with KNN-Based Composite Memory for Dialoguecited by 53
  6. 2017End-to-End Task-Completion Neural Dialogue Systemscited by 52
  7. 2019Robust Zero-Shot Cross-Domain Slot Filling with Example Valuescited by 38
  8. 2020Schema-Guided Dialogue State Tracking Task at DSTC8cited by 32

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 6; 2023: 4; 2024: 1; 2025: 0; 2026: 1.

16 papers.

Sort:

By area:

  1. 2021PLATO-XL: Exploring the Large-scale Pre-training of Dialogue Generationcited by 37
  2. 2021TOD-DA: Towards Boosting the Robustness of Task-oriented Dialogue Modeling on Spoken Conversationscited by 11
  3. 2023GripRank: Bridging the Gap between Retrieval and Generation via the Generative Knowledge Improved Passage Rankingcited by 11
  4. 2024Should We Fine-Tune or RAG? Evaluating Different Techniques to Adapt LLMs for Dialoguecited by 7
  5. 2022OPERA: Harmonizing Task-Oriented Dialogs and Information Seeking Experiencecited by 5
  6. 2023Task-oriented Document-Grounded Dialog Systems by HLTPR@RWTH for DSTC9 and DSTC10cited by 4
  7. 2021End-to-End Task-Oriented Dialog Modeling with Semi-Structured Knowledge Managementcited by 3
  8. 2022Controllable Factuality in Document-Grounded Dialog Systems Using a Noisy Channel Modelcited by 3
  9. 2021GKS: Graph-based Knowledge Selector for Task-oriented Dialog Systemcited by 1
  10. 2022Towards Generalized Models for Task-oriented Dialogue Modeling on Spoken Conversationscited by 1
  11. 2022Robust Unstructured Knowledge Access in Conversational Dialogue with ASR Errorscited by 1
  12. 2022Mind the Knowledge Gap: A Survey of Knowledge-enhanced Dialogue Systemscited by 1
4 more
  1. 2023Retrieval-Augmented Neural Response Generation Using Logical Reasoning and Relevance Scoringcited by 1
  2. 2026HiNS: Hierarchical Negative Sampling for More Comprehensive Memory Retrieval Embedding Modelcited by 1
  3. 2022External Knowledge Selection with Weighted Negative Sampling in Knowledge-grounded Task-oriented Dialogue Systemscited by 0
  4. 2023A Graph-to-Text Approach to Knowledge-Grounded Response Generation in Human-Robot Interactioncited by 0