Zero-shot Generalization in Dialog State Tracking through Generative Question Answering

2021-01-20 · EACL 2021 2 · Shuyang Li, Jin Cao, Mukund Sridhar, Henghui Zhu, Shang-Wen Li, Wael Hamza, Julian McAuley

Dialog State Tracking (DST), an integral part of modern dialog systems, aims to track user preferences and constraints (slots) in task-oriented dialogs. In real-world settings with constantly changing services, DST systems must generalize to new domains and unseen slot types. Existing methods for DST do not generalize well to new slot names and many require known ontologies of slot types and values for inference. We introduce a novel ontology-free framework that supports natural language queries for unseen constraints and slots in multi-domain task-oriented dialogs. Our approach is based on generative question-answering using a conditional language model pre-trained on substantive English sentences. Our model improves joint goal accuracy in zero-shot domain adaptation settings by up to 9% (absolute) over the previous state-of-the-art on the MultiWOZ 2.1 dataset.

📄 PDF Abstract BibTeX arXiv:2101.08333

Code (0)

등록된 구현이 없습니다.

Tasks

dialog state trackingDomain Adaptation Generative Question AnsweringLanguage ModelingLanguage Modelling Natural Language Queries Question Answering Zero-shot Generalization

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.

Schema-Guided Dialogue State Tracking Task at DSTC8

2020-02-02 · Abhinav Rastogi, Xiaoxue Zang, Srinivas Sunkara, Raghav Gupta 외

This paper gives an overview of the Schema-Guided Dialogue State Tracking task of the 8th Dialogue System Technology Challenge. The goal of this task is to develop dialogue state tracking models suitable for large-scale …

Data Augmentation Dialogue State Tracking Zero-shot Generalization

Zero-Shot Dialogue State Tracking via Cross-Task Transfer

2021-09-10 · EMNLP 2021 11 · Zhaojiang Lin, Bing Liu, Andrea Madotto, Seungwhan Moon 외

Zero-shot transfer learning for dialogue state tracking (DST) enables us to handle a variety of task-oriented dialogue domains without the expense of collecting in-domain data. In this work, we propose to transfer the \t…

Dialogue State Tracking Question Answering Transfer Learning

Fine-Tuning BERT for Schema-Guided Zero-Shot Dialogue State Tracking

2020-02-01 · Yu-Ping Ruan, Zhen-Hua Ling, Jia-Chen Gu, Quan Liu

We present our work on Track 4 in the Dialogue System Technology Challenges 8 (DSTC8). The DSTC8-Track 4 aims to perform dialogue state tracking (DST) under the zero-shot settings, in which the model needs to generalize …

Dialogue State Tracking Natural Language Understanding Prediction slot-filling+2

Schema Augmentation for Zero-Shot Domain Adaptation in Dialogue State Tracking

2024-10-31 · Christopher Richardson, Roshan Sharma, Neeraj Gaur, Parisa Haghani 외

Zero-shot domain adaptation for dialogue state tracking (DST) remains a challenging problem in task-oriented dialogue (TOD) systems, where models must generalize to target domains unseen at training time. Current large l…

Data Augmentation Dialogue State Tracking Domain Adaptation Language Modeling+3

Divide, Conquer, and Combine: Mixture of Semantic-Independent Experts for Zero-Shot Dialogue State Tracking

2023-06-01 · Qingyue Wang, Liang Ding, Yanan Cao, Yibing Zhan 외

Zero-shot transfer learning for Dialogue State Tracking (DST) helps to handle a variety of task-oriented dialogue domains without the cost of collecting in-domain data. Existing works mainly study common data- or model-l…

Dialogue State Tracking Mixture-of-Experts Transfer Learning