activity
20182022
most citedOpen-Domain Targeted Sentiment Analysis via Span-Based Extraction and Classification

23 citations · 49 across the 5 of their papers we have counts for

collaborators

12 papers

cs.SD2022

Unsupervised Voice-Face Representation Learning by Cross-Modal Prototype Contrast

Boqing Zhu, Kele Xu, Changjian Wang +4

We present an approach to learn voice-face representations from the talking face videos, without any identity labels. Previous works employ cross-modal instance discrimination task…

eess.AS202021 cited

Audio Tagging by Cross Filtering Noisy Labels

Boqing Zhu, Kele Xu, Qiuqiang Kong +2

High quality labeled datasets have allowed deep learning to achieve impressive results on many sound analysis tasks. Yet, it is labor-intensive to accurately annotate large amount…

cs.MM2020

Multi-Representation Knowledge Distillation For Audio Classification

Liang Gao, Kele Xu, Huaimin Wang +1

As an important component of multimedia analysis tasks, audio classification aims to discriminate between different audio signal types and has received intensive attention due to i…

cs.CL2019

A Multi-Type Multi-Span Network for Reading Comprehension that Requires Discrete Reasoning

Minghao Hu, Yuxing Peng, Zhen Huang +1

Rapid progress has been made in the field of reading comprehension and question answering, where several systems have achieved human parity in some simplified settings. However, th…

cs.CL20195 cited

Retrieve, Read, Rerank: Towards End-to-End Multi-Document Reading Comprehension

Minghao Hu, Yuxing Peng, Zhen Huang +1

This paper considers the reading comprehension task in which multiple documents are given as input. Prior work has shown that a pipeline of retriever, reader, and reranker can impr…

cs.CL201923 cited

Open-Domain Targeted Sentiment Analysis via Span-Based Extraction and Classification

Minghao Hu, Yuxing Peng, Zhen Huang +2

Open-domain targeted sentiment analysis aims to detect opinion targets along with their sentiment polarities from a sentence. Prior work typically formulates this task as a sequenc…