Enhancing Dialogue State Tracking Models through LLM-backed User-Agents Simulation

• URL: http://arxiv.org/abs/2405.13037v1
• Date: Fri, 17 May 2024 07:00:05 GMT
• Title: Enhancing Dialogue State Tracking Models through LLM-backed User-Agents Simulation
• Authors: Cheng Niu, Xingguang Wang, Xuxin Cheng, Juntong Song, Tong Zhang,
• Abstract summary: GPT-4 is used to simulate the user and agent interaction, generating thousands of annotated dialogues with DST labels. A two-stage fine-tuning on LLaMA 2 is performed on the generated data and the real data for the DST prediction. Our approach is also capable of adapting to the dynamic demands in real-world scenarios, generating dialogues in new domains swiftly.
• Score: 12.93942316816741
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Dialogue State Tracking (DST) is designed to monitor the evolving dialogue state in the conversations and plays a pivotal role in developing task-oriented dialogue systems. However, obtaining the annotated data for the DST task is usually a costly endeavor. In this paper, we focus on employing LLMs to generate dialogue data to reduce dialogue collection and annotation costs. Specifically, GPT-4 is used to simulate the user and agent interaction, generating thousands of dialogues annotated with DST labels. Then a two-stage fine-tuning on LLaMA 2 is performed on the generated data and the real data for the DST prediction. Experimental results on two public DST benchmarks show that with the generated dialogue data, our model performs better than the baseline trained solely on real data. In addition, our approach is also capable of adapting to the dynamic demands in real-world scenarios, generating dialogues in new domains swiftly. After replacing dialogue segments in any domain with the corresponding generated ones, the model achieves comparable performance to the model trained on real data.

Related papers

• Are LLMs Robust for Spoken Dialogues? [10.855403629160921]
  Large Pre-Trained Language Models have demonstrated state-of-the-art performance in different downstream tasks. Most of the publicly available datasets and benchmarks on task-oriented dialogues focus on written conversations. We have evaluated the performance of LLMs for spoken task-oriented dialogues on the DSTC11 test sets.
  arXiv  Detail & Related papers  (2024-01-04T14:36:38Z)
• OPAL: Ontology-Aware Pretrained Language Model for End-to-End Task-Oriented Dialogue [40.62090743056549]
  This paper presents an ontology-aware pretrained language model (OPAL) for end-to-end task-oriented dialogue (TOD) Unlike chit-chat dialogue models, task-oriented dialogue models fulfill at least two task-specific modules: dialogue state tracker (DST) and response generator (RG)
  arXiv  Detail & Related papers  (2022-09-10T04:38:27Z)
• 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)
• A Model-Agnostic Data Manipulation Method for Persona-based Dialogue Generation [107.82729587882397]
  It is expensive to scale up current persona-based dialogue datasets. Each data sample in this task is more complex to learn with than conventional dialogue data. We propose a data manipulation method, which is model-agnostic to be packed with any persona-based dialogue generation model.
  arXiv  Detail & Related papers  (2022-04-21T03:49:54Z)
• In-Context Learning for Few-Shot Dialogue State Tracking [55.91832381893181]
  We propose an in-context (IC) learning framework for few-shot dialogue state tracking (DST) A large pre-trained language model (LM) takes a test instance and a few annotated examples as input, and directly decodes the dialogue states without any parameter updates. This makes the LM more flexible and scalable compared to prior few-shot DST work when adapting to new domains and scenarios.
  arXiv  Detail & Related papers  (2022-03-16T11:58:24Z)
• Dialogue Summaries as Dialogue States (DS2), Template-Guided Summarization for Few-shot Dialogue State Tracking [16.07100713414678]
  Few-shot dialogue state tracking (DST) is a realistic solution to this problem. We propose to reformulate dialogue state tracking as a dialogue summarization problem.
  arXiv  Detail & Related papers  (2022-03-03T07:54:09Z)
• Dual Learning for Dialogue State Tracking [44.679185483585364]
  Dialogue state tracking (DST) is to estimate the dialogue state at each turn. Due to the dependency on complicated dialogue history contexts, DST data annotation is more expensive than single-sentence language understanding. We propose a novel dual-learning framework to make full use of unlabeled data.
  arXiv  Detail & Related papers  (2020-09-22T10:15:09Z)
• Dialogue Distillation: Open-Domain Dialogue Augmentation Using Unpaired Data [61.71319905364992]
  We propose a novel data augmentation method for training open-domain dialogue models by utilizing unpaired data. A data-level distillation process is first proposed to construct augmented dialogues where both post and response are retrieved from the unpaired data. A ranking module is employed to filter out low-quality dialogues. A model-level distillation process is employed to distill a teacher model trained on high-quality paired data to augmented dialogue pairs.
  arXiv  Detail & Related papers  (2020-09-20T13:06:38Z)
• Modeling Long Context for Task-Oriented Dialogue State Generation [51.044300192906995]
  We propose a multi-task learning model with a simple yet effective utterance tagging technique and a bidirectional language model. Our approaches attempt to solve the problem that the performance of the baseline significantly drops when the input dialogue context sequence is long. In our experiments, our proposed model achieves a 7.03% relative improvement over the baseline, establishing a new state-of-the-art joint goal accuracy of 52.04% on the MultiWOZ 2.0 dataset.
  arXiv  Detail & Related papers  (2020-04-29T11:02:25Z)
• 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.