Continual Dialogue State Tracking via Reason-of-Select Distillation

• URL: http://arxiv.org/abs/2408.09846v2
• Date: Wed, 16 Oct 2024 03:15:20 GMT
• Title: Continual Dialogue State Tracking via Reason-of-Select Distillation
• Authors: Yujie Feng, Bo Liu, Xiaoyu Dong, Zexin Lu, Li-Ming Zhan, Albert Y. S. Lam, Xiao-Ming Wu,
• Abstract summary: We introduce the Reason-of-Select (RoS) distillation method by enhancing smaller models with a novel'meta-reasoning' capability. The domain bootstrapping process enhances the model's ability to dissect intricate dialogues from multiple possible values. Two novel improvements, "multi-value resolution" strategy and Semantic Contrastive Reasoning Selection method, significantly enhance RoS.
• Score: 20.844176879145927
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: An ideal dialogue system requires continuous skill acquisition and adaptation to new tasks while retaining prior knowledge. Dialogue State Tracking (DST), vital in these systems, often involves learning new services and confronting catastrophic forgetting, along with a critical capability loss termed the "Value Selection Quandary." To address these challenges, we introduce the Reason-of-Select (RoS) distillation method by enhancing smaller models with a novel 'meta-reasoning' capability. Meta-reasoning employs an enhanced multi-domain perspective, combining fragments of meta-knowledge from domain-specific dialogues during continual learning. This transcends traditional single-perspective reasoning. The domain bootstrapping process enhances the model's ability to dissect intricate dialogues from multiple possible values. Its domain-agnostic property aligns data distribution across different domains, effectively mitigating forgetting. Additionally, two novel improvements, "multi-value resolution" strategy and Semantic Contrastive Reasoning Selection method, significantly enhance RoS by generating DST-specific selection chains and mitigating hallucinations in teachers' reasoning, ensuring effective and reliable knowledge transfer. Extensive experiments validate the exceptional performance and robust generalization capabilities of our method. The source code is provided for reproducibility.

Related papers

• Few-Shot Dialogue Summarization via Skeleton-Assisted Prompt Transfer in Prompt Tuning [47.336815771549524]
  Skeleton-Assisted Prompt Transfer improves prompt transfer from dialogue state tracking to dialogue summarization. We propose a novel approach with perturbation-based probes requiring neither annotation effort nor domain knowledge. In-depth analyses demonstrate the effectiveness of our method in facilitating cross-task knowledge transfer in few-shot dialogue summarization.
  arXiv  Detail & Related papers  (2023-05-20T03:32:48Z)
• Choice Fusion as Knowledge for Zero-Shot Dialogue State Tracking [5.691339955497443]
  zero-shot dialogue state tracking (DST) tracks user's requirements in task-oriented dialogues without training on desired domains. We propose CoFunDST, which is trained on domain-agnostic QA datasets and directly uses candidate choices of slot-values as knowledge for zero-shot dialogue-state generation. Our proposed model achieves outperformed joint goal accuracy compared to existing zero-shot DST approaches in most domains on the MultiWOZ 2.1.
  arXiv  Detail & Related papers  (2023-02-25T07:32:04Z)
• 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)
• There Is No Standard Answer: Knowledge-Grounded Dialogue Generation with Adversarial Activated Multi-Reference Learning [29.093220439736527]
  Knowledge-grounded conversation (KGC) shows excellent potential to deliver an engaging and informative response. Existing approaches emphasize selecting one golden knowledge given a particular dialogue context, overlooking the one-to-many phenomenon in dialogue. We propose a series of metrics to systematically assess the one-to-many efficacy of existing KGC models.
  arXiv  Detail & Related papers  (2022-10-22T14:43:33Z)
• Continual Prompt Tuning for Dialog State Tracking [58.66412648276873]
  A desirable dialog system should be able to continually learn new skills without forgetting old ones. We present Continual Prompt Tuning, a parameter-efficient framework that not only avoids forgetting but also enables knowledge transfer between tasks.
  arXiv  Detail & Related papers  (2022-03-13T13:22:41Z)
• Continual Learning for Natural Language Generation in Task-oriented Dialog Systems [72.92029584113676]
  Natural language generation (NLG) is an essential component of task-oriented dialog systems. We study NLG in a "continual learning" setting to expand its knowledge to new domains or functionalities incrementally. The major challenge towards this goal is catastrophic forgetting, meaning that a continually trained model tends to forget the knowledge it has learned before.
  arXiv  Detail & Related papers  (2020-10-02T10:32:29Z)
• Modelling Hierarchical Structure between Dialogue Policy and Natural Language Generator with Option Framework for Task-oriented Dialogue System [49.39150449455407]
  HDNO is an option framework for designing latent dialogue acts to avoid designing specific dialogue act representations. We test HDNO on MultiWoz 2.0 and MultiWoz 2.1, the datasets on multi-domain dialogues, in comparison with word-level E2E model trained with RL, LaRL and HDSA.
  arXiv  Detail & Related papers  (2020-06-11T20:55:28Z)
• 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)
• 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)
• Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue [51.513276162736844]
  We propose a sequential latent variable model as the first approach to this matter. The model named sequential knowledge transformer (SKT) can keep track of the prior and posterior distribution over knowledge.
  arXiv  Detail & Related papers  (2020-02-18T11:59:59Z)

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.