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

arXiv: https://arxiv.org/abs/2112.08844 · HTML: https://mlsanity.com/paper/2112.08844/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 37 references that are in the map.
- First posted on arXiv 16 Dec 2021.

## Builds on (most cited first, 25 of 25)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Wizard of Wikipedia: Knowledge-Powered Conversational agents](https://mlsanity.com/paper/1811.01241/) (2018)
- [Datasets: A Community Library for Natural Language Processing](https://mlsanity.com/paper/2109.02846/) (2021)
- [DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts](https://mlsanity.com/paper/2105.03023/) (2021)
- [Noisy Channel Language Model Prompting for Few-Shot Text Classification](https://mlsanity.com/paper/2108.04106/) (2021)
- [On Using Monolingual Corpora in Neural Machine Translation](https://mlsanity.com/paper/1503.03535/) (2015)
- [Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset](https://mlsanity.com/paper/1909.05358/) (2019)
- [doc2dial: A Goal-Oriented Document-Grounded Dialogue Dataset](https://mlsanity.com/paper/2011.06623/) (2020)
- [A Density Ratio Approach to Language Model Fusion in End-To-End Automatic Speech Recognition](https://mlsanity.com/paper/2002.11268/) (2020)
- [Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access](https://mlsanity.com/paper/2006.03533/) (2020)
- [Simple and Effective Noisy Channel Modeling for Neural Machine Translation](https://mlsanity.com/paper/1908.05731/) (2019)
- [Efficient Retrieval Augmented Generation from Unstructured Knowledge for Task-Oriented Dialog](https://mlsanity.com/paper/2102.04643/) (2021)
- [Joint Contextual Modeling for ASR Correction and Language Understanding](https://mlsanity.com/paper/2002.00750/) (2020)
- ["How Robust r u?": Evaluating Task-Oriented Dialogue Systems on Spoken Conversations](https://mlsanity.com/paper/2109.13489/) (2021)
- [Pretraining the Noisy Channel Model for Task-Oriented Dialogue](https://mlsanity.com/paper/2103.10518/) (2021)
- [The Neural Noisy Channel](https://mlsanity.com/paper/1611.02554/) (2016)
- [Are Neural Open-Domain Dialog Systems Robust to Speech Recognition Errors in the Dialog History? An Empirical Study](https://mlsanity.com/paper/2008.07683/) (2020)
- [Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access Track in DSTC9](https://mlsanity.com/paper/2101.09276/) (2021)
- [Can I Be of Further Assistance? Using Unstructured Knowledge Access to Improve Task-oriented Conversational Modeling](https://mlsanity.com/paper/2106.09174/) (2021)
- [NVIDIA NeMo Neural Machine Translation Systems for English-German and English-Russian News and Biomedical Tasks at WMT21](https://mlsanity.com/paper/2111.08634/) (2021)
- [Investigation of Error Simulation Techniques for Learning Dialog Policies for Conversational Error Recovery](https://mlsanity.com/paper/1911.03378/) (2019)

## Built on by (most cited first, 5 of 5)

- [Response Generation in Longitudinal Dialogues: Which Knowledge Representation Helps?](https://mlsanity.com/paper/2305.15908/) (2023)
- [Task-oriented Document-Grounded Dialog Systems by HLTPR@RWTH for DSTC9 and DSTC10](https://mlsanity.com/paper/2304.07101/) (2023)
- [Controllable Factuality in Document-Grounded Dialog Systems Using a Noisy Channel Model](https://mlsanity.com/paper/2210.17418/) (2022)
- [Leveraging Few-Shot Data Augmentation and Waterfall Prompting for Response Generation](https://mlsanity.com/paper/2308.01080/) (2023)
- [Joint Speech and Text Training for LLM-Based End-to-End Spoken Dialogue State Tracking](https://mlsanity.com/paper/2511.22503/) (2025)

## 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.