# Converse, Focus and Guess -- Towards Multi-Document Driven Dialogue

arXiv: https://arxiv.org/abs/2102.02435 · HTML: https://mlsanity.com/paper/2102.02435/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 25 references that are in the map.
- First posted on arXiv 4 Feb 2021.

## Builds on (most cited first, 19 of 19)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [CoQA: A Conversational Question Answering Challenge](https://mlsanity.com/paper/1808.07042/) (2018)
- [Wizard of Wikipedia: Knowledge-Powered Conversational agents](https://mlsanity.com/paper/1811.01241/) (2018)
- [Key-Value Memory Networks for Directly Reading Documents](https://mlsanity.com/paper/1606.03126/) (2016)
- [A Knowledge-Grounded Neural Conversation Model](https://mlsanity.com/paper/1702.01932/) (2017)
- [GuessWhat?! Visual object discovery through multi-modal dialogue](https://mlsanity.com/paper/1611.08481/) (2016)
- [Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning](https://mlsanity.com/paper/1703.06585/) (2017)
- [Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems](https://mlsanity.com/paper/1804.08217/) (2018)
- [A User Simulator for Task-Completion Dialogues](https://mlsanity.com/paper/1612.05688/) (2016)
- [Global-to-local Memory Pointer Networks for Task-Oriented Dialogue](https://mlsanity.com/paper/1901.04713/) (2019)
- [Towards End-to-End Reinforcement Learning of Dialogue Agents for Information Access](https://mlsanity.com/paper/1609.00777/) (2016)
- [Incremental Transformer with Deliberation Decoder for Document Grounded Conversations](https://mlsanity.com/paper/1907.08854/) (2019)
- [Towards End-to-End Learning for Dialog State Tracking and Management using Deep Reinforcement Learning](https://mlsanity.com/paper/1606.02560/) (2016)
- [Extending Neural Generative Conversational Model using External Knowledge Sources](https://mlsanity.com/paper/1809.05524/) (2018)
- [Visual Dialogue State Tracking for Question Generation](https://mlsanity.com/paper/1911.07928/) (2019)
- [Playing 20 Question Game with Policy-Based Reinforcement Learning](https://mlsanity.com/paper/1808.07645/) (2018)
- [Guessing State Tracking for Visual Dialogue](https://mlsanity.com/paper/2002.10340/) (2020)
- [Label-Wise Document Pre-Training for Multi-Label Text Classification](https://mlsanity.com/paper/2008.06695/) (2020)

## Built on by (most cited first, 1 of 1)

- [An Asynchronous Updating Reinforcement Learning Framework for Task-oriented Dialog System](https://mlsanity.com/paper/2305.02718/) (2023)

## Abstract (arXiv)

We propose a novel task, Multi-Document Driven Dialogue (MD3), in which an agent can guess the target document that the user is interested in by leading a dialogue. To benchmark progress, we introduce a new dataset of GuessMovie, which contains 16,881 documents, each describing a movie, and associated 13,434 dialogues. Further, we propose the MD3 model. Keeping guessing the target document in mind, it converses with the user conditioned on both document engagement and user feedback. In order to incorporate large-scale external documents into the dialogue, it pretrains a document representation which is sensitive to attributes it talks about an object. Then it tracks dialogue state by detecting evolvement of document belief and attribute belief, and finally optimizes dialogue policy in principle of entropy decreasing and reward increasing, which is expected to successfully guess the user's target in a minimum number of turns. Experiments show that our method significantly outperforms several strong baseline methods and is very close to human's performance.