Výsledky vyhledávání

Report

Dialogue State Tracking with Multi-Level Fusion of Predicted Dialogue States and Conversations

Autor: Zhou, Jingyao, Wu, Haipang, Lin, Zehao, Li, Guodun, Zhang, Yin

Most recently proposed approaches in dialogue state tracking (DST) leverage the context and the last dialogue states to track current dialogue states, which are often slot-value pairs. Although the context contains the complete dialogue information,

Externí odkaz: http://arxiv.org/abs/2107.05168

Zobrazit plný text záznamu

Report

Efficient Dialogue State Tracking by Masked Hierarchical Transformer

Autor: Mao, Min, Liu, Jiasheng, Zhou, Jingyao, Wu, Haipang

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 lang

Externí odkaz: http://arxiv.org/abs/2106.14433

Zobrazit plný text záznamu

Report

A Knowledge-Grounded Dialog System Based on Pre-Trained Language Models

Autor: Zhang, Weijie, Chen, Jiaoxuan, Wu, Haipang, Wan, Sanhui, Li, Gongfeng

We present a knowledge-grounded dialog system developed for the ninth Dialog System Technology Challenge (DSTC9) Track 1 - Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access. We leverage transfer learning wit

Externí odkaz: http://arxiv.org/abs/2106.14444

Zobrazit plný text záznamu

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Vyhledávací nástroje:

Upřesnit hledání