activity
20202022
most citedUnsupervised Hashing with Contrastive Information Bottleneck

7 citations · 16 across the 7 of their papers we have counts for

collaborators

7 papers

cs.CL2022

MCSCSet: A Specialist-annotated Dataset for Medical-domain Chinese Spelling Correction

Wangjie Jiang, Zhihao Ye, Zijing Ou +7

Chinese Spelling Correction (CSC) is gaining increasing attention due to its promise of automatically detecting and correcting spelling errors in Chinese texts. Despite its extensi…

cs.CV20224 cited

Modeling Semantic Composition with Syntactic Hypergraph for Video Question Answering

Zenan Xu, Wanjun Zhong, Qinliang Su +2

A key challenge in video question answering is how to realize the cross-modal semantic alignment between textual concepts and corresponding visual objects. Existing methods mostly…

cs.IR2021

Refining BERT Embeddings for Document Hashing via Mutual Information Maximization

Zijing Ou, Qinliang Su, Jianxing Yu +3

Existing unsupervised document hashing methods are mostly established on generative models. Due to the difficulties of capturing long dependency structures, these methods rarely mo…

cs.IR20213 cited

Integrating Semantics and Neighborhood Information with Graph-Driven Generative Models for Document Retrieval

Zijing Ou, Qinliang Su, Jianxing Yu +5

With the need of fast retrieval speed and small memory footprint, document hashing has been playing a crucial role in large-scale information retrieval. To generate high-quality ha…

cs.CV20217 cited

Unsupervised Hashing with Contrastive Information Bottleneck

Zexuan Qiu, Qinliang Su, Zijing Ou +2

Many unsupervised hashing methods are implicitly established on the idea of reconstructing the input data, which basically encourages the hashing codes to retain as much informatio…

cs.CL20212 cited

Imperfect also Deserves Reward: Multi-Level and Sequential Reward Modeling for Better Dialog Management

Zhengxu Hou, Bang Liu, Ruihui Zhao +4

For task-oriented dialog systems, training a Reinforcement Learning (RL) based Dialog Management module suffers from low sample efficiency and slow convergence speed due to the spa…