Counterfactual Matters: Intrinsic Probing For Dialogue State Tracking

no code implementations • EANCS 2021 • Yi Huang, Junlan Feng, Xiaoting Wu, Xiaoyu Du

Our findings are: the performance variance of generative DSTs is not only due to the model structure itself, but can be attributed to the distribution of cross-domain values.

Dialogue State Tracking Task-Oriented Dialogue Systems

Towards Low-Resource Semi-Supervised Dialogue Generation with Meta-Learning

no code implementations • Findings of the Association for Computational Linguistics 2020 • Yi Huang, Junlan Feng, Shuo Ma, Xiaoyu Du, Xiaoting Wu

In this paper, we propose a meta-learning based semi-supervised explicit dialogue state tracker (SEDST) for neural dialogue generation, denoted as MEDST.

Dialogue Generation Meta-Learning

Meta-Reinforced Multi-Domain State Generator for Dialogue Systems

no code implementations • ACL 2020 • Yi Huang, Junlan Feng, Min Hu, Xiaoting Wu, Xiaoyu Du, Shuo Ma

The state-of-the-art accuracy for DST is below 50{\%} for a multi-domain dialogue task.

Domain Adaptation Meta-Learning

Audio-Visual Kinship Verification

no code implementations • 24 Jun 2019 • Xiaoting Wu, Eric Granger, Xiaoyi Feng

Then, early and late fusion methods are evaluated on the TALKIN dataset for the study of kinship verification with both face and voice modalities.

Face Verification