Efficient Dialogue State Tracking by Masked Hierarchical Transformer

Autor:	Mao, Min, Liu, Jiasheng, Zhou, Jingyao, Wu, Haipang
Rok vydání:	2021
Předmět:	Computer Science - Computation and Language
Druh dokumentu:	Working Paper
Popis:	This paper describes our approach to DSTC 9 Track 2: Cross-lingual Multi-domain Dialog State Tracking, the task goal is to build a Cross-lingual dialog state tracker with a training set in rich resource language and a testing set in low resource language. We formulate a method for joint learning of slot operation classification task and state tracking task respectively. Furthermore, we design a novel mask mechanism for fusing contextual information about dialogue, the results show the proposed model achieves excellent performance on DSTC Challenge II with a joint accuracy of 62.37% and 23.96% in MultiWOZ(en - zh) dataset and CrossWOZ(zh - en) dataset, respectively. Comment: 6 pages, 3 figures
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2106.14433 Zobrazit plný text záznamu View this record from Arxiv