mlsanityData to 7 Oct 2026

Adapting Document-Grounded Dialog Systems to Spoken Conversations using Data Augmentation and a Noisy Channel Model

arXiv 2112.08844 ↗First posted 16 Dec 2021cs.CL cs.AI cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

This paper summarizes our submission to Task 2 of the second track of the 10th Dialog System Technology Challenge (DSTC10) "Knowledge-grounded Task-oriented Dialogue Modeling on Spoken Conversations". Similar to the previous year's iteration, the task consists of three subtasks: detecting whether a turn is knowledge seeking, selecting the relevant knowledge document and finally generating a grounded response. This year, the focus lies on adapting the system to noisy ASR transcripts. We explore different approaches to make the models more robust to this type of input and to adapt the generated responses to the style of spoken conversations. For the latter, we get the best results with a noisy channel model that additionally reduces the number of short and generic responses. Our best system achieved the 1st rank in the automatic and the 3rd rank in the human evaluation of the challenge.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 25 of its 37 references that are in the map. First posted on arXiv 16 Dec 2021.

Builds on

25 of 37 references.

References · 25

  1. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  4. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  5. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  6. 2018Wizard of Wikipedia: Knowledge-Powered Conversational agentscited by 530
  7. 2021Datasets: A Community Library for Natural Language Processingcited by 526
  8. 2021DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Expertscited by 434
  9. 2021Noisy Channel Language Model Prompting for Few-Shot Text Classificationcited by 163
  10. 2015On Using Monolingual Corpora in Neural Machine Translationcited by 149
  11. 2019Taskmaster-1: Toward a Realistic and Diverse Dialog Datasetcited by 139
  12. 2020doc2dial: A Goal-Oriented Document-Grounded Dialogue Datasetcited by 88
13 more
  1. 2020A Density Ratio Approach to Language Model Fusion in End-To-End Automatic Speech Recognitioncited by 73
  2. 2020Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Accesscited by 58
  3. 2019Simple and Effective Noisy Channel Modeling for Neural Machine Translationcited by 37
  4. 2021Efficient Retrieval Augmented Generation from Unstructured Knowledge for Task-Oriented Dialogcited by 33
  5. 2020Joint Contextual Modeling for ASR Correction and Language Understandingcited by 30
  6. 2021"How Robust r u?": Evaluating Task-Oriented Dialogue Systems on Spoken Conversationscited by 30
  7. 2021Pretraining the Noisy Channel Model for Task-Oriented Dialoguecited by 23
  8. 2016The Neural Noisy Channelcited by 19
  9. 2020Are Neural Open-Domain Dialog Systems Robust to Speech Recognition Errors in the Dialog History? An Empirical Studycited by 19
  10. 2021Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access Track in DSTC9cited by 10
  11. 2021Can I Be of Further Assistance? Using Unstructured Knowledge Access to Improve Task-oriented Conversational Modelingcited by 8
  12. 2021NVIDIA NeMo Neural Machine Translation Systems for English-German and English-Russian News and Biomedical Tasks at WMT21cited by 8
  13. 2019Investigation of Error Simulation Techniques for Learning Dialog Policies for Conversational Error Recoverycited by 5

Built on by

Cited by year

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

5 papers.

  1. 2023Response Generation in Longitudinal Dialogues: Which Knowledge Representation Helps?cited by 6
  2. 2023Task-oriented Document-Grounded Dialog Systems by HLTPR@RWTH for DSTC9 and DSTC10cited by 4
  3. 2022Controllable Factuality in Document-Grounded Dialog Systems Using a Noisy Channel Modelcited by 3
  4. 2023Leveraging Few-Shot Data Augmentation and Waterfall Prompting for Response Generationcited by 1
  5. 2025Joint Speech and Text Training for LLM-Based End-to-End Spoken Dialogue State Trackingcited by 1