MTSS: Learn from Multiple Domain Teachers and Become a Multi-domain Dialogue Expert

• URL: http://arxiv.org/abs/2005.10450v1
• Date: Thu, 21 May 2020 03:40:02 GMT
• Title: MTSS: Learn from Multiple Domain Teachers and Become a Multi-domain Dialogue Expert
• Authors: Shuke Peng, Feng Ji, Zehao Lin, Shaobo Cui, Haiqing Chen, Yin Zhang
• Abstract summary: 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.
• Score: 24.010266171280342
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: How to build a high-quality multi-domain dialogue system is a challenging work due to its complicated and entangled dialogue state space among each domain, which seriously limits the quality of dialogue policy, and further affects the generated response. In this paper, we propose a novel method to acquire a satisfying policy and subtly circumvent the knotty dialogue state representation problem in the multi-domain setting. Inspired by real school teaching scenarios, our method is composed of multiple domain-specific teachers and a universal student. Each individual teacher only focuses on one specific domain and learns its corresponding domain knowledge and dialogue policy based on a precisely extracted single domain dialogue state representation. Then, these domain-specific teachers impart their domain knowledge and policies to a universal student model and collectively make this student model a multi-domain dialogue expert. Experiment results show that our method reaches competitive results with SOTAs in both multi-domain and single domain setting.

Related papers

• A Unified Data Augmentation Framework for Low-Resource Multi-Domain Dialogue Generation [52.0964459842176]
  Current state-of-the-art dialogue systems heavily rely on extensive training datasets. We propose a novel data textbfAugmentation framework for textbfMulti-textbfDomain textbfDialogue textbfGeneration, referred to as textbfAMD$2$G. The AMD$2$G framework consists of a data augmentation process and a two-stage training approach: domain-agnostic training and domain adaptation training.
  arXiv  Detail & Related papers  (2024-06-14T09:52:27Z)
• ChatPLUG: Open-Domain Generative Dialogue System with Internet-Augmented Instruction Tuning for Digital Human [76.62897301298699]
  ChatPLUG is a Chinese open-domain dialogue system for digital human applications that instruction finetunes on a wide range of dialogue tasks in a unified internet-augmented format. We show that modelname outperforms state-of-the-art Chinese dialogue systems on both automatic and human evaluation. We deploy modelname to real-world applications such as Smart Speaker and Instant Message applications with fast inference.
  arXiv  Detail & Related papers  (2023-04-16T18:16:35Z)
• PoE: a Panel of Experts for Generalized Automatic Dialogue Assessment [58.46761798403072]
  A model-based automatic dialogue evaluation metric (ADEM) is expected to perform well across multiple domains. Despite significant progress, an ADEM that works well in one domain does not necessarily generalize to another. We propose a Panel of Experts (PoE) network that consists of a shared transformer encoder and a collection of lightweight adapters.
  arXiv  Detail & Related papers  (2022-12-18T02:26:50Z)
• Graph Neural Network Policies and Imitation Learning for Multi-Domain Task-Oriented Dialogues [0.716879432974126]
  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.
  arXiv  Detail & Related papers  (2022-10-11T08:29:10Z)
• 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)
• A Student-Teacher Architecture for Dialog Domain Adaptation under the Meta-Learning Setting [42.80034363734555]
  It is essential to develop algorithms that can adapt to different domains efficiently when building data-driven dialog models. We propose an efficient domain adaptive task-oriented dialog system model, which incorporates a meta-teacher model. We evaluate our model on two multi-domain datasets, MultiWOZ and Google-Guided Dialogue, and achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2021-04-06T17:31:28Z)
• 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)
• Not all domains are equally complex: Adaptive Multi-Domain Learning [98.25886129591974]
  We propose an adaptive parameterization approach to deep neural networks for multi-domain learning. The proposed approach performs on par with the original approach while reducing by far the number of parameters.
  arXiv  Detail & Related papers  (2020-03-25T17:16:00Z)

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.