Improving Longer-range Dialogue State Tracking
원문 초록
Dialogue state tracking (DST) is a pivotal component in task-oriented dialogue systems. While it is relatively easy for a DST model to capture belief states in short conversations, the task of DST becomes more challenging as the length of a dialogue increases due to the injection of more distracting contexts. In this paper, we aim to improve the overall performance of DST with a special focus on handling longer dialogues. We tackle this problem from three perspectives: 1) A model designed to enable hierarchical slot status prediction; 2) Balanced training procedure for generic and task-specific language understanding; 3) Data perturbation which enhances the model's ability in handling longer conversations. We conduct experiments on the MultiWOZ benchmark, and demonstrate the effectiveness of each component via a set of ablation tests, especially on longer conversations.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Confidence Estimation for LLM-Based Dialogue State Tracking
Simulating Task-Oriented Dialogues with State Transition Graphs and Large Language Models
JMultiWOZ: A Large-Scale Japanese Multi-Domain Task-Oriented Dialogue Dataset
Exploring the Viability of Synthetic Audio Data for Audio-Based Dialogue State Tracking
Turn-Level Active Learning for Dialogue State Tracking
Towards LLM-driven Dialogue State Tracking
토론
이 논문과 연결된 포럼 글이 아직 없습니다.