# Pan More Gold from the Sand: Refining Open-domain Dialogue Training with Noisy Self-Retrieval Generation

arXiv: https://arxiv.org/abs/2201.11367 · HTML: https://mlsanity.com/paper/2201.11367/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 39 references that are in the map.
- First posted on arXiv 27 Jan 2022.

## Builds on (most cited first, 28 of 28)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://mlsanity.com/paper/1911.00536/) (2019)
- [Personalizing Dialogue Agents: I have a dog, do you have pets too?](https://mlsanity.com/paper/1801.07243/) (2018)
- [Recipes for building an open-domain chatbot](https://mlsanity.com/paper/2004.13637/) (2020)
- [Wizard of Wikipedia: Knowledge-Powered Conversational agents](https://mlsanity.com/paper/1811.01241/) (2018)
- [Towards a Human-like Open-Domain Chatbot](https://mlsanity.com/paper/2001.09977/) (2020)
- [Beyond Goldfish Memory: Long-Term Open-Domain Conversation](https://mlsanity.com/paper/2107.07567/) (2021)
- [Internet-Augmented Dialogue Generation](https://mlsanity.com/paper/2107.07566/) (2021)
- [PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable](https://mlsanity.com/paper/1910.07931/) (2019)
- [ParlAI: A Dialog Research Software Platform](https://mlsanity.com/paper/1705.06476/) (2017)
- [Retrieve and Refine: Improved Sequence Generation Models For Dialogue](https://mlsanity.com/paper/1808.04776/) (2018)
- [PLATO-2: Towards Building an Open-Domain Chatbot via Curriculum Learning](https://mlsanity.com/paper/2006.16779/) (2020)
- [A Large-Scale Chinese Short-Text Conversation Dataset](https://mlsanity.com/paper/2008.03946/) (2020)
- [BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Data](https://mlsanity.com/paper/2106.06169/) (2021)
- [Few-Shot Bot: Prompt-Based Learning for Dialogue Systems](https://mlsanity.com/paper/2110.08118/) (2021)
- [Skeleton-to-Response: Dialogue Generation Guided by Retrieval Memory](https://mlsanity.com/paper/1809.05296/) (2018)
- [SparTerm: Learning Term-based Sparse Representation for Fast Text Retrieval](https://mlsanity.com/paper/2010.00768/) (2020)
- [Response Generation by Context-aware Prototype Editing](https://mlsanity.com/paper/1806.07042/) (2018)
- [Zero-Resource Knowledge-Grounded Dialogue Generation](https://mlsanity.com/paper/2008.12918/) (2020)
- [Evaluating Prerequisite Qualities for Learning End-to-End Dialog Systems](https://mlsanity.com/paper/1511.06931/) (2015)

## Built on by (most cited first, 2 of 2)

- [KPT: Keyword-guided Pre-training for Grounded Dialog Generation](https://mlsanity.com/paper/2212.01739/) (2022)
- [ReSee: Responding through Seeing Fine-grained Visual Knowledge in Open-domain Dialogue](https://mlsanity.com/paper/2305.13602/) (2023)

## Abstract (arXiv)

Real human conversation data are complicated, heterogeneous, and noisy, from which building open-domain dialogue systems remains a challenging task. In fact, such dialogue data still contains a wealth of information and knowledge, however, they are not fully explored. In this paper, we show existing open-domain dialogue generation methods that memorize context-response paired data with autoregressive or encode-decode language models underutilize the training data. Different from current approaches, using external knowledge, we explore a retrieval-generation training framework that can take advantage of the heterogeneous and noisy training data by considering them as "evidence". In particular, we use BERTScore for retrieval, which gives better qualities of the evidence and generation. Experiments over publicly available datasets demonstrate that our method can help models generate better responses, even such training data are usually impressed as low-quality data. Such performance gain is comparable with those improved by enlarging the training set, even better. We also found that the model performance has a positive correlation with the relevance of the retrieved evidence. Moreover, our method performed well on zero-shot experiments, which indicates that our method can be more robust to real-world data.