paper-with-me

홈 › Papers

SF-DST: Few-Shot Self-Feeding Reading Comprehension Dialogue State Tracking with Auxiliary Task

2022-09-16 · Jihyun Lee, Gary Geunbae Lee

Few-shot dialogue state tracking (DST) model tracks user requests in dialogue with reliable accuracy even with a small amount of data. In this paper, we introduce an ontology-free few-shot DST with self-feeding belief state input. The self-feeding belief state input increases the accuracy in multi-turn dialogue by summarizing previous dialogue. Also, we newly developed a slot-gate auxiliary task. This new auxiliary task helps classify whether a slot is mentioned in the dialogue. Our model achieved the best score in a few-shot setting for four domains on multiWOZ 2.0.

📄 PDF Abstract BibTeX arXiv:2209.07742

Code (0)

등록된 구현이 없습니다.

Tasks

Dialogue State TrackingReading Comprehension

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

From Machine Reading Comprehension to Dialogue State Tracking: Bridging the Gap

2020-04-13 · WS 2020 7 · Shuyang Gao, Sanchit Agarwal, Tagyoung Chung, Di Jin 외

Dialogue state tracking (DST) is at the heart of task-oriented dialogue systems. However, the scarcity of labeled data is an obstacle to building accurate and robust state tracking systems that work across a variety of d…

Dialogue State TrackingMachine Reading ComprehensionMultiple-choiceReading Comprehension+1

CSS: Combining Self-training and Self-supervised Learning for Few-shot Dialogue State Tracking

2022-10-11 · Haoning Zhang, Junwei Bao, Haipeng Sun, Huaishao Luo 외

Few-shot dialogue state tracking (DST) is a realistic problem that trains the DST model with limited labeled data. Existing few-shot methods mainly transfer knowledge learned from external labeled dialogue data (e.g., fr…

Dialogue State TrackingMachine Reading ComprehensionQuestion AnsweringReading Comprehension+1

Self- and Pseudo-self-supervised Prediction of Speaker and Key-utterance for Multi-party Dialogue Reading Comprehension

2021-09-08 · Findings (EMNLP) 2021 11 · Yiyang Li, Hai Zhao

Multi-party dialogue machine reading comprehension (MRC) brings tremendous challenge since it involves multiple speakers at one dialogue, resulting in intricate speaker information flows and noisy dialogue contexts. To a…

Machine Reading ComprehensionQuestion AnsweringReading Comprehension

DREAM: A Challenge Dataset and Models for Dialogue-Based Reading Comprehension

2019-02-01 · Kai Sun, Dian Yu, Jianshu Chen, Dong Yu 외

We present DREAM, the first dialogue-based multiple-choice reading comprehension dataset. Collected from English-as-a-foreign-language examinations designed by human experts to evaluate the comprehension level of Chinese…

Dialogue UnderstandingMultiple-choiceReading ComprehensionSentence+1

DREAM: A Challenge Data Set and Models for Dialogue-Based Reading Comprehension

2019-03-01 · TACL 2019 3 · Kai Sun, Dian Yu, Jianshu Chen, Dong Yu 외

We present DREAM, the first dialogue-based multiple-choice reading comprehension data set. Collected from English as a Foreign Language examinations designed by human experts to evaluate the comprehension level of Chines…

Dialogue UnderstandingMultiple-choiceReading ComprehensionSentence+1