Graph Neural Network Policies and Imitation Learning for Multi-Domain Task-Oriented Dialogues

• URL: http://arxiv.org/abs/2210.05252v1
• Date: Tue, 11 Oct 2022 08:29:10 GMT
• Title: Graph Neural Network Policies and Imitation Learning for Multi-Domain Task-Oriented Dialogues
• Authors: Thibault Cordier, Tanguy Urvoy, Fabrice Lef\`evre, Lina M. Rojas-Barahona
• Abstract summary: Task-oriented dialogue systems are designed to achieve specific goals while conversing with humans. In practice, they may have to handle simultaneously several domains and tasks. We show that structured policies based on graph neural networks combined with different degrees of imitation learning can effectively handle multi-domain dialogues.
• Score: 0.716879432974126
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Task-oriented dialogue systems are designed to achieve specific goals while conversing with humans. In practice, they may have to handle simultaneously several domains and tasks. The dialogue manager must therefore be able to take into account domain changes and plan over different domains/tasks in order to deal with multidomain dialogues. However, learning with reinforcement in such context becomes difficult because the state-action dimension is larger while the reward signal remains scarce. Our experimental results suggest that structured policies based on graph neural networks combined with different degrees of imitation learning can effectively handle multi-domain dialogues. The reported experiments underline the benefit of structured policies over standard policies.

Related papers

• Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agents [121.46051697742608]
  We introduce a new dialogue policy planning paradigm to strategize dialogue problems with a tunable language model plug-in named PPDPP. Specifically, we develop a novel training framework to facilitate supervised fine-tuning over available human-annotated data. PPDPP consistently and substantially outperforms existing approaches on three different proactive dialogue applications.
  arXiv  Detail & Related papers  (2023-11-01T03:20:16Z)
• Manual-Guided Dialogue for Flexible Conversational Agents [84.46598430403886]
  How to build and use dialogue data efficiently, and how to deploy models in different domains at scale can be critical issues in building a task-oriented dialogue system. We propose a novel manual-guided dialogue scheme, where the agent learns the tasks from both dialogue and manuals. Our proposed scheme reduces the dependence of dialogue models on fine-grained domain ontology, and makes them more flexible to adapt to various domains.
  arXiv  Detail & Related papers  (2022-08-16T08:21:12Z)
• Reinforcement Learning of Multi-Domain Dialog Policies Via Action Embeddings [38.51601073819774]
  Learning task-oriented dialog policies via reinforcement learning typically requires large amounts of interaction with users. We propose to leverage data from across different dialog domains, thereby reducing the amount of data required from each given domain. We show how this approach is capable of learning with significantly less interaction with users, with a reduction of 35% in the number of dialogs required to learn, and to a higher level of proficiency than training separate policies for each domain on a set of simulated domains.
  arXiv  Detail & Related papers  (2022-07-01T14:49:05Z)
• An empirical assessment of deep learning approaches to task-oriented dialog management [3.9023554886892438]
  We perform an assessment of different configurations for deep-learned dialog management with three dialog corpora from different application domains. Our results have allowed us to identify several aspects that can have an impact on accuracy, including the approaches used for feature extraction and input representation.
  arXiv  Detail & Related papers  (2021-08-07T16:05:48Z)
• Distributed Structured Actor-Critic Reinforcement Learning for Universal Dialogue Management [29.57382819573169]
  We focus on devising a policy that chooses which dialogue action to respond to the user. The sequential system decision-making process can be abstracted into a partially observable Markov decision process. In the past few years, there are many deep reinforcement learning (DRL) algorithms, which use neural networks (NN) as function approximators.
  arXiv  Detail & Related papers  (2020-09-22T05:39:31Z)
• Meta Dialogue Policy Learning [58.045067703675095]
  We propose Deep Transferable Q-Network (DTQN) to utilize shareable low-level signals between domains. We decompose the state and action representation space into feature subspaces corresponding to these low-level components. In experiments, our model outperforms baseline models in terms of both success rate and dialogue efficiency.
  arXiv  Detail & Related papers  (2020-06-03T23:53:06Z)
• MTSS: Learn from Multiple Domain Teachers and Become a Multi-domain Dialogue Expert [24.010266171280342]
  We propose a novel method to acquire a satisfying policy in multi-domain setting. Inspired by real school teaching scenarios, our method is composed of multiple domain-specific teachers and a universal student. Experiment results show that our method reaches competitive results with SOTAs in both multi-domain and single domain setting.
  arXiv  Detail & Related papers  (2020-05-21T03:40:02Z)
• UniConv: A Unified Conversational Neural Architecture for Multi-domain Task-oriented Dialogues [101.96097419995556]
  "UniConv" is a novel unified neural architecture for end-to-end conversational systems in task-oriented dialogues. We conduct comprehensive experiments in dialogue state tracking, context-to-text, and end-to-end settings on the MultiWOZ2.1 benchmark.
  arXiv  Detail & Related papers  (2020-04-29T16:28:22Z)
• Masking Orchestration: Multi-task Pretraining for Multi-role Dialogue Representation Learning [50.5572111079898]
  Multi-role dialogue understanding comprises a wide range of diverse tasks such as question answering, act classification, dialogue summarization etc. While dialogue corpora are abundantly available, labeled data, for specific learning tasks, can be highly scarce and expensive. In this work, we investigate dialogue context representation learning with various types unsupervised pretraining tasks.
  arXiv  Detail & Related papers  (2020-02-27T04:36:52Z)
• Non-Autoregressive Dialog State Tracking [122.2328875457225]
  We propose a novel framework of Non-Autoregressive Dialog State Tracking (NADST) NADST can factor in potential dependencies among domains and slots to optimize the models towards better prediction of dialogue states as a complete set rather than separate slots. Our results show that our model achieves the state-of-the-art joint accuracy across all domains on the MultiWOZ 2.1 corpus.
  arXiv  Detail & Related papers  (2020-02-19T06:39:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.