paper-with-me

홈 › Papers

Cost-Sensitive Active Learning for Dialogue State Tracking

2018-07-01 · WS 2018 7 · Kaige Xie, Cheng Chang, Liliang Ren, Lu Chen, Kai Yu

Dialogue state tracking (DST), when formulated as a supervised learning problem, relies on labelled data. Since dialogue state annotation usually requires labelling all turns of a single dialogue and utilizing context information, it is very expensive to annotate all available unlabelled data. In this paper, a novel cost-sensitive active learning framework is proposed based on a set of new dialogue-level query strategies. This is the first attempt to apply active learning for dialogue state tracking. Experiments on DSTC2 show that active learning with mixed data query strategies can effectively achieve the same DST performance with significantly less data annotation compared to traditional training approaches.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Active LearningDialogue State Tracking

Methods 이 논문이 사용한 방법론

DST Dynamic sparse training methods train neural networks in a sparse manner, starting with an initial sparse mask, and periodically updating the mask based on some criteria.

Similar Papers 제목 키워드 기반

Turn-Level Active Learning for Dialogue State Tracking

2023-10-23 · Zihan Zhang, Meng Fang, Fanghua Ye, Ling Chen 외

Dialogue state tracking (DST) plays an important role in task-oriented dialogue systems. However, collecting a large amount of turn-by-turn annotated dialogue data is costly and inefficient. In this paper, we propose a n…

Active LearningDialogue State TrackingTask-Oriented Dialogue Systems

Context-Sensitive Generation Network for Handing Unknown Slot Values in Dialogue State Tracking

2020-05-08 · Puhai Yang, He-Yan Huang, Xian-Ling Mao

As a key component in a dialogue system, dialogue state tracking plays an important role. It is very important for dialogue state tracking to deal with the problem of unknown slot values. As far as we known, almost all e…

Dialogue State Tracking

Grounding Description-Driven Dialogue State Trackers with Knowledge-Seeking Turns

2023-09-23 · Alexandru Coca, Bo-Hsiang Tseng, Jinghong Chen, Weizhe Lin 외

Schema-guided dialogue state trackers can generalise to new domains without further training, yet they are sensitive to the writing style of the schemata. Augmenting the training set with human or synthetic schema paraph…

Sensitivity

Conversational Human Audio-visual Talking Dialogue Generation

2026-07-02 · Junhao Song, Lluis Guasch, Xilin He, Zhongyu Yang 외 arxiv

Large-scale dyadic interactive audio-visual dialogue (DIAD) datasets provide fundamental data resources for developing humanoid interactive virtual agents and digital humans. However, collecting such data is time-consumi…

Dialogue Generation

Amendable Generation for Dialogue State Tracking

2021-10-29 · EMNLP (NLP4ConvAI) 2021 11 · Xin Tian, Liankai Huang, Yingzhan Lin, Siqi Bao 외

In task-oriented dialogue systems, recent dialogue state tracking methods tend to perform one-pass generation of the dialogue state based on the previous dialogue state. The mistakes of these models made at the current t…

Dialogue State TrackingMulti-domain Dialogue State TrackingTask-Oriented Dialogue Systems