# Coarse-to-Fine Knowledge Selection for Document Grounded Dialogs

arXiv: https://arxiv.org/abs/2302.11849 · HTML: https://mlsanity.com/paper/2302.11849/

## Key facts

- Cited by 6 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 23 Feb 2023.

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

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [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)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering](https://mlsanity.com/paper/2007.01282/) (2020)
- [Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval](https://mlsanity.com/paper/2007.00808/) (2020)
- [RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2010.08191/) (2020)
- [Knowledge-Grounded Dialogue Generation with Pre-trained Language Models](https://mlsanity.com/paper/2010.08824/) (2020)
- [GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injection](https://mlsanity.com/paper/2111.14592/) (2021)
- [Re2G: Retrieve, Rerank, Generate](https://mlsanity.com/paper/2207.06300/) (2022)
- [doc2dial: A Goal-Oriented Document-Grounded Dialogue Dataset](https://mlsanity.com/paper/2011.06623/) (2020)
- [Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue](https://mlsanity.com/paper/2002.07510/) (2020)
- [Learning to Select Knowledge for Response Generation in Dialog Systems](https://mlsanity.com/paper/1902.04911/) (2019)
- [MultiDoc2Dial: Modeling Dialogues Grounded in Multiple Documents](https://mlsanity.com/paper/2109.12595/) (2021)
- [A Survey on Complex Question Answering over Knowledge Base: Recent Advances and Challenges](https://mlsanity.com/paper/2007.13069/) (2020)
- [Incremental Transformer with Deliberation Decoder for Document Grounded Conversations](https://mlsanity.com/paper/1907.08854/) (2019)
- [RefNet: A Reference-aware Network for Background Based Conversation](https://mlsanity.com/paper/1908.06449/) (2019)
- [DialogueCSE: Dialogue-based Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2109.12599/) (2021)
- [Interactive Matching Network for Multi-Turn Response Selection in Retrieval-Based Chatbots](https://mlsanity.com/paper/1901.01824/) (2019)
- [Difference-aware Knowledge Selection for Knowledge-grounded Conversation Generation](https://mlsanity.com/paper/2009.09378/) (2020)
- [CGoDial: A Large-Scale Benchmark for Chinese Goal-oriented Dialog Evaluation](https://mlsanity.com/paper/2211.11617/) (2022)
- [UniGDD: A Unified Generative Framework for Goal-Oriented Document-Grounded Dialogue](https://mlsanity.com/paper/2204.07770/) (2022)
- [Dial2vec: Self-Guided Contrastive Learning of Unsupervised Dialogue Embeddings](https://mlsanity.com/paper/2210.15332/) (2022)

## Built on by (most cited first, 6 of 6)

- [Unleashing Potential of Evidence in Knowledge-Intensive Dialogue Generation](https://mlsanity.com/paper/2309.08380/) (2023)
- [Diversify Question Generation with Retrieval-Augmented Style Transfer](https://mlsanity.com/paper/2310.14503/) (2023)
- [Causal Document-Grounded Dialogue Pre-training](https://mlsanity.com/paper/2305.10927/) (2023)
- [Mitigating the Impact of False Negatives in Dense Retrieval with Contrastive Confidence Regularization](https://mlsanity.com/paper/2401.00165/) (2023)
- [How Does Knowledge Selection Help Retrieval Augmented Generation?](https://mlsanity.com/paper/2410.13258/) (2024)
- [Cross-lingual Data Augmentation for Document-grounded Dialog Systems in Low Resource Languages](https://mlsanity.com/paper/2305.14949/) (2023)

## Abstract (arXiv)

Multi-document grounded dialogue systems (DGDS) belong to a class of conversational agents that answer users' requests by finding supporting knowledge from a collection of documents. Most previous studies aim to improve the knowledge retrieval model or propose more effective ways to incorporate external knowledge into a parametric generation model. These methods, however, focus on retrieving knowledge from mono-granularity language units (e.g. passages, sentences, or spans in documents), which is not enough to effectively and efficiently capture precise knowledge in long documents. This paper proposes Re3G, which aims to optimize both coarse-grained knowledge retrieval and fine-grained knowledge extraction in a unified framework. Specifically, the former efficiently finds relevant passages in a retrieval-and-reranking process, whereas the latter effectively extracts finer-grain spans within those passages to incorporate into a parametric answer generation model (BART, T5). Experiments on DialDoc Shared Task demonstrate the effectiveness of our method.