Search Results for author: Zijing Ou

Found 10 papers, 8 papers with code

Training Discrete Energy-Based Models with Energy Discrepancy

no code implementations14 Jul 2023 Tobias Schröder, Zijing Ou, Yingzhen Li, Andrew B. Duncan

Training energy-based models (EBMs) on discrete spaces is challenging because sampling over such spaces can be difficult.

Energy Discrepancies: A Score-Independent Loss for Energy-Based Models

1 code implementation NeurIPS 2023 Tobias Schröder, Zijing Ou, Jen Ning Lim, Yingzhen Li, Sebastian J. Vollmer, Andrew B. Duncan

Energy-based models are a simple yet powerful class of probabilistic models, but their widespread adoption has been limited by the computational burden of training them.

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

1 code implementation21 Oct 2022 Wangjie Jiang, Zhihao Ye, Zijing Ou, Ruihui Zhao, Jianguang Zheng, Yi Liu, Siheng Li, Bang Liu, Yujiu Yang, Yefeng Zheng

In this work, we define the task of Medical-domain Chinese Spelling Correction and propose MCSCSet, a large scale specialist-annotated dataset that contains about 200k samples.

Optical Character Recognition Optical Character Recognition (OCR) +1

Modeling Semantic Composition with Syntactic Hypergraph for Video Question Answering

no code implementations13 May 2022 Zenan Xu, Wanjun Zhong, Qinliang Su, Zijing Ou, Fuwei Zhang

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

Question Answering Semantic Composition +1

Learning Neural Set Functions Under the Optimal Subset Oracle

1 code implementation3 Mar 2022 Zijing Ou, Tingyang Xu, Qinliang Su, Yingzhen Li, Peilin Zhao, Yatao Bian

Learning neural set functions becomes increasingly more important in many applications like product recommendation and compound selection in AI-aided drug discovery.

Anomaly Detection Drug Discovery +2

Tell Me How to Survey: Literature Review Made Simple with Automatic Reading Path Generation

1 code implementation12 Oct 2021 Jiayuan Ding, Tong Xiang, Zijing Ou, Wangyang Zuo, Ruihui Zhao, Chenghua Lin, Yefeng Zheng, Bang Liu

In this paper, we introduce a new task named Reading Path Generation (RPG) which aims at automatically producing a path of papers to read for a given query.

Unsupervised Hashing with Contrastive Information Bottleneck

1 code implementation13 May 2021 Zexuan Qiu, Qinliang Su, Zijing Ou, Jianxing Yu, Changyou Chen

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 information of original data as possible.

Contrastive Learning

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

1 code implementation NAACL 2021 Zhengxu Hou, Bang Liu, Ruihui Zhao, Zijing Ou, Yafei Liu, Xi Chen, Yefeng Zheng

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 sparse rewards in RL. To solve this problem, many strategies have been proposed to give proper rewards when training RL, but their rewards lack interpretability and cannot accurately estimate the distribution of state-action pairs in real dialogs.

Management reinforcement-learning +1

Cannot find the paper you are looking for? You can Submit a new open access paper.