activity
20182022
most citedUndistillable: Making A Nasty Teacher That CANNOT teach students

19 citations · 31 across the 7 of their papers we have counts for

collaborators

13 papers

cs.CL20221 cited

End-to-end Spoken Conversational Question Answering: Task, Dataset and Model

Chenyu You, Nuo Chen, Fenglin Liu +3

In spoken question answering, the systems are designed to answer questions from contiguous text spans within the related speech transcripts. However, the most natural way that huma…

cs.LG2022

KerGNNs: Interpretable Graph Neural Networks with Graph Kernels

Aosong Feng, Chenyu You, Shiqiang Wang +1

Graph kernels are historically the most widely-used technique for graph classification tasks. However, these methods suffer from limited performance because of the hand-crafted com…

cs.CL2021

Self-supervised Contrastive Cross-Modality Representation Learning for Spoken Question Answering

Chenyu You, Nuo Chen, Yuexian Zou

Spoken question answering (SQA) requires fine-grained understanding of both spoken documents and questions for the optimal answer prediction. In this paper, we propose novel traini…

cs.CL2021

Self-supervised Dialogue Learning for Spoken Conversational Question Answering

Nuo Chen, Chenyu You, Yuexian Zou

In spoken conversational question answering (SCQA), the answer to the corresponding question is generated by retrieving and then analyzing a fixed spoken document, including multi-…

cs.LG202119 cited

Undistillable: Making A Nasty Teacher That CANNOT teach students

Haoyu Ma, Tianlong Chen, Ting-Kuei Hu +3

Knowledge Distillation (KD) is a widely used technique to transfer knowledge from pre-trained teacher models to (usually more lightweight) student models. However, in certain situa…

cs.CL20203 cited

Adaptive Bi-directional Attention: Exploring Multi-Granularity Representations for Machine Reading Comprehension

Nuo Chen, Fenglin Liu, Chenyu You +2

Recently, the attention-enhanced multi-layer encoder, such as Transformer, has been extensively studied in Machine Reading Comprehension (MRC). To predict the answer, it is common…