paper-with-me

홈 › Papers

Neural Dialogue State Tracking with Temporally Expressive Networks

2020-09-16 · Findings of the Association for Computational Linguistics 2020 · Junfan Chen, Richong Zhang, Yongyi Mao, Jie Xu

Dialogue state tracking (DST) is an important part of a spoken dialogue system. Existing DST models either ignore temporal feature dependencies across dialogue turns or fail to explicitly model temporal state dependencies in a dialogue. In this work, we propose Temporally Expressive Networks (TEN) to jointly model the two types of temporal dependencies in DST. The TEN model utilizes the power of recurrent networks and probabilistic graphical models. Evaluating on standard datasets, TEN is demonstrated to be effective in improving the accuracy of turn-level-state prediction and the state aggregation.

📄 PDF Abstract BibTeX arXiv:2009.07615

Code (1)

BDBC-KG-NLP/TEN_EMNLP2020 공식 구현 pytorch

Tasks

Dialogue 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

Spoken Dialogue for Information Navigation

2018-07-01 · WS 2018 7 · Alex Papangelis, ros, Panagiotis Papadakos, Yannis Stylianou 외

Aiming to expand the current research paradigm for training conversational AI agents that can address real-world challenges, we take a step away from traditional slot-filling goal-oriented spoken dialogue systems (SDS) a…

Information Retrievalslot-fillingSlot FillingSpoken Dialogue Systems

Parallel Interactive Networks for Multi-Domain Dialogue State Generation

2020-09-16 · EMNLP 2020 11 · Junfan Chen, Richong Zhang, Yongyi Mao, Jie Xu

The dependencies between system and user utterances in the same turn and across different turns are not fully considered in existing multidomain dialogue state tracking (MDST) models. In this study, we argue that the inc…

Dialogue State TrackingMulti-domain Dialogue State Tracking

Comprehensive Study: How the Context Information of Different Granularity Affects Dialogue State Tracking?

2021-05-08 · ACL 2021 5 · Puhai Yang, Heyan Huang, Xian-Ling Mao

Dialogue state tracking (DST) plays a key role in task-oriented dialogue systems to monitor the user's goal. In general, there are two strategies to track a dialogue state: predicting it from scratch and updating it from…

Dialogue State TrackingFew-Shot LearningTask-Oriented Dialogue Systems

Act-Aware Slot-Value Predicting in Multi-Domain Dialogue State Tracking

2022-08-04 · Ruolin Su, Ting-Wei Wu, Biing-Hwang Juang

As an essential component in task-oriented dialogue systems, dialogue state tracking (DST) aims to track human-machine interactions and generate state representations for managing the dialogue. Representations of dialogu…

Dialogue State TrackingMachine Reading ComprehensionMulti-domain Dialogue State TrackingReading Comprehension+1

Capturing Dialogue State Variable Dependencies with an Energy-based Neural Dialogue State Tracker

2019-09-01 · WS 2019 9 · Anh Duong Trinh, Robert J. Ross, John D. Kelleher

Dialogue state tracking requires the population and maintenance of a multi-slot frame representation of the dialogue state. Frequently, dialogue state tracking systems assume independence between slot values within a fra…

Dialogue State TrackingPredictionStructured Prediction