paper-with-me

홈 › Papers

Rethinking Dialogue State Tracking with Reasoning

2020-05-27 · Lizi Liao, Yunshan Ma, Wenqiang Lei, Tat-Seng Chua

Tracking dialogue states to better interpret user goals and feed downstream policy learning is a bottleneck in dialogue management. Common practice has been to treat it as a problem of classifying dialogue content into a set of pre-defined slot-value pairs, or generating values for different slots given the dialogue history. Both have limitations on considering dependencies that occur on dialogues, and are lacking of reasoning capabilities. 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, a large-scale human-human dialogue dataset across multiple domains.

📄 PDF Abstract BibTeX arXiv:2005.13129

Code (0)

등록된 구현이 없습니다.

Tasks

Dialogue ManagementDialogue State TrackingManagement

Similar Papers 제목 키워드 기반

GEM: Graph-Enhanced Mixture-of-Experts with ReAct Agents for Dialogue State Tracking

2026-05-06 · Ziqi Zhu, Adithya Suresh, Tomal Deb, Iman Abbasnejad arxiv

Dialogue State Tracking (DST) requires precise extraction of structured information from multi-domain conversations, a task where Large Language Models (LLMs) struggle despite their impressive general capabilities. We pr…

Computational EfficiencyDialogue State TrackingGraph Neural Network

Dialogue State Tracking with Multi-Level Fusion of Predicted Dialogue States and Conversations

2021-07-12 · SIGDIAL (ACL) 2021 7 · Jingyao Zhou, Haipang Wu, Zehao Lin, Guodun Li 외

Most recently proposed approaches in dialogue state tracking (DST) leverage the context and the last dialogue states to track current dialogue states, which are often slot-value pairs. Although the context contains the c…

Dialogue State Tracking

Multi-Modal Dialogue State Tracking for Playing GuessWhich Game

2024-08-15 · Wei Pang, Ruixue Duan, Jinfu Yang, Ning li

GuessWhich is an engaging visual dialogue game that involves interaction between a Questioner Bot (QBot) and an Answer Bot (ABot) in the context of image-guessing. In this game, QBot's objective is to locate a concealed …

Dialogue State TrackingVisual Reasoning

Dialogue State Tracking with Explicit Slot Connection Modeling

2020-07-01 · ACL 2020 6 · Yawen Ouyang, Moxin Chen, Xin-yu Dai, Yinggong Zhao 외

Recent proposed approaches have made promising progress in dialogue state tracking (DST). However, in multi-domain scenarios, ellipsis and reference are frequently adopted by users to express values that have been mentio…

Dialogue State Tracking

Continual Dialogue State Tracking via Reason-of-Select Distillation

2024-08-19 · Yujie Feng, Bo Liu, Xiaoyu Dong, Zexin Lu 외

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 …

Continual LearningDialogue State TrackingTransfer Learning