SF-DST: Few-Shot Self-Feeding Reading Comprehension Dialogue State Tracking with Auxiliary Task

• URL: http://arxiv.org/abs/2209.07742v1
• Date: Fri, 16 Sep 2022 06:54:25 GMT
• Title: SF-DST: Few-Shot Self-Feeding Reading Comprehension Dialogue State Tracking with Auxiliary Task
• Authors: Jihyun Lee, Gary Geunbae Lee
• Abstract summary: Few-shot dialogue state tracking model tracks user requests in dialogue with reliable accuracy even with a small amount of data. Self-feeding belief state input increases the accuracy in multi-turn dialogue by summarizing previous dialogue. New auxiliary task helps classify whether a slot is mentioned in the dialogue.
• Score: 17.763227077651173
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Few-shot dialogue state tracking (DST) model tracks user requests in dialogue with reliable accuracy even with a small amount of data. In this paper, we introduce an ontology-free few-shot DST with self-feeding belief state input. The self-feeding belief state input increases the accuracy in multi-turn dialogue by summarizing previous dialogue. Also, we newly developed a slot-gate auxiliary task. This new auxiliary task helps classify whether a slot is mentioned in the dialogue. Our model achieved the best score in a few-shot setting for four domains on multiWOZ 2.0.

Related papers

• Dialogue State Distillation Network with Inter-Slot Contrastive Learning for Dialogue State Tracking [25.722458066685046]
  Dialogue State Tracking (DST) aims to extract users' intentions from the dialogue history. Currently, most existing approaches suffer from error propagation and are unable to dynamically select relevant information. We propose a Dialogue State Distillation Network (DSDN) to utilize relevant information of previous dialogue states.
  arXiv  Detail & Related papers  (2023-02-16T11:05:24Z)
• GODEL: Large-Scale Pre-Training for Goal-Directed Dialog [119.1397031992088]
  We introduce GODEL, a large pre-trained language model for dialog. We show that GODEL outperforms state-of-the-art pre-trained dialog models in few-shot fine-tuning setups. A novel feature of our evaluation methodology is the introduction of a notion of utility that assesses the usefulness of responses.
  arXiv  Detail & Related papers  (2022-06-22T18:19:32Z)
• A Slot Is Not Built in One Utterance: Spoken Language Dialogs with Sub-Slots [67.69407159704328]
  This paper defines a new task named Sub-Slot based Task-Oriented Dialog (SSTOD) The dataset includes a total of 40K dialogs and 500K utterances from four different domains: Chinese names, phone numbers, ID numbers and license plate numbers. We find some new linguistic phenomena and interactive manners in SSTOD which raise critical challenges of building dialog agents for the task.
  arXiv  Detail & Related papers  (2022-03-21T07:10:19Z)
• 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)
• Zero-Shot Dialogue State Tracking via Cross-Task Transfer [69.70718906395182]
  We propose to transfer the textitcross-task knowledge from general question answering (QA) corpora for the zero-shot dialogue state tracking task. Specifically, we propose TransferQA, a transferable generative QA model that seamlessly combines extractive QA and multi-choice QA. In addition, we introduce two effective ways to construct unanswerable questions, namely, negative question sampling and context truncation.
  arXiv  Detail & Related papers  (2021-09-10T03:57:56Z)
• Improving Longer-range Dialogue State Tracking [22.606650177804966]
  Dialogue state tracking (DST) is a pivotal component in task-oriented dialogue systems. In this paper, we aim to improve the overall performance of DST with a special focus on handling longer dialogues.
  arXiv  Detail & Related papers  (2021-02-27T02:44:28Z)
• Rethinking Dialogue State Tracking with Reasoning [76.0991910623001]
  This paper proposes to track dialogue states gradually with reasoning over dialogue turns with the help of the back-end data. Empirical results demonstrate that our method significantly outperforms the state-of-the-art methods by 38.6% in terms of joint belief accuracy for MultiWOZ 2.1.
  arXiv  Detail & Related papers  (2020-05-27T02:05:33Z)
• 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)
• Goal-Oriented Multi-Task BERT-Based Dialogue State Tracker [0.1864131501304829]
  State Tracking (DST) is a core component of virtual assistants such as Alexa or Siri. In this work, we propose a GOaL-Oriented Multi-task BERT-based dialogue state tracker (GOLOMB)
  arXiv  Detail & Related papers  (2020-02-05T22:56:12Z)

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.