Robust Dialogue State Tracking with Weak Supervision and Sparse Data
원문 초록
Generalising dialogue state tracking (DST) to new data is especially challenging due to the strong reliance on abundant and fine-grained supervision during training. Sample sparsity, distributional shift and the occurrence of new concepts and topics frequently lead to severe performance degradation during inference. In this paper we propose a training strategy to build extractive DST models without the need for fine-grained manual span labels. Two novel input-level dropout methods mitigate the negative impact of sample sparsity. We propose a new model architecture with a unified encoder that supports value as well as slot independence by leveraging the attention mechanism. We combine the strengths of triple copy strategy DST and value matching to benefit from complementary predictions without violating the principle of ontology independence. Our experiments demonstrate that an extractive DST model can be trained without manual span labels. Our architecture and training strategies improve robustness towards sample sparsity, new concepts and topics, leading to state-of-the-art performance on a range of benchmarks. We further highlight our model's ability to effectively learn from non-dialogue data.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Know Your Mistakes: Towards Preventing Overreliance on Task-Oriented Conversational AI Through Accountability Modeling
Beyond Ontology in Dialogue State Tracking for Goal-Oriented Chatbot
A Zero-Shot Open-Vocabulary Pipeline for Dialogue Understanding
Confidence Estimation for LLM-Based Dialogue State Tracking
Continual Dialogue State Tracking via Reason-of-Select Distillation
TaSL: Continual Dialog State Tracking via Task Skill Localization and Consolidation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.