Chang Tian — accepted AI-conference papers

2024

A Generic Method for Fine-grained Category Discovery in Natural Language Texts

Chang Tian, Matthew B. Blaschko, Wenpeng Yin, Mingzhe Xing, Yinliang Yue, Marie-Francine Moens

EMNLP 2024main

Fine-grained category discovery using only coarse-grained supervision is a cost-effective yet challenging task. Previous training methods focus on aligning query samples with positive samples and distancing them from negatives. They often neglect intra-category and inter-category semantic similariti…

Cited by 3 Source ↗PDF ↗code ↗Scholar ↗

2022

Anti-Overestimation Dialogue Policy Learning for Task-Completion Dialogue System

Chang Tian, Wenpeng Yin, Marie-Francine Moens

NAACL 2022findings

A dialogue policy module is an essential part of task-completion dialogue systems. Recently, increasing interest has focused on reinforcement learning (RL)-based dialogue policy. Its favorable performance and wise action decisions rely on an accurate estimation of action values. The overestimation p…

Cited by 5 Source ↗PDF ↗Scholar ↗