Search Results for author: Yidong Chen

Found 34 papers, 12 papers with code

Towards Robust Neural Machine Translation with Iterative Scheduled Data-Switch Training

1 code implementation COLING 2022 Zhongjian Miao, Xiang Li, Liyan Kang, Wen Zhang, Chulun Zhou, Yidong Chen, Bin Wang, Min Zhang, Jinsong Su

Most existing methods on robust neural machine translation (NMT) construct adversarial examples by injecting noise into authentic examples and indiscriminately exploit two types of examples.

Machine Translation NMT +2

XMU’s Simultaneous Translation System at NAACL 2021

no code implementations NAACL (AutoSimTrans) 2021 Shuangtao Li, Jinming Hu, Boli Wang, Xiaodong Shi, Yidong Chen

This paper describes our two systems submitted to the simultaneous translation evaluation at the 2nd automatic simultaneous translation workshop.


一种基于IDLSTM+CRF的中文主地域抽取方法(A Chinese Main Location Extraction Method based on IDLSTM+CRF)

no code implementations CCL 2021 Yiqi Tong, PeiGen Ye, Biao Fu, Yidong Chen, Xiaodong Shi

“新闻文本通常会涉及多个地域, 主地域则描述了文本舆情内容的地域属性, 是进行舆情分析的关键属性。目前深度学习领域针对主地域自动抽取的研究还比较少。基于此, 本文构建了一个基于IDLSTM+CRF的主地域抽取系统。该系统通过地名识别、主地域抽取、主地域补全三大模块实现对主地域标签的自动抽取和补全。在公开数据集上的实验结果表明, 我们的方法在地名识别任务上要优于BiLSTM+CRF等模型。而对于主地域抽取任务, 目前还没有标准的中文主地域评测集合。针对该问题, 我们标注并开源了1226条验证集和1500条测试集。最终, 我们的主地域抽取系统在两个集合上分别取得了91. 7%和84. 8%的抽取准确率, 并成功运用于线上生产环境。”

Conditional Variational Autoencoder for Sign Language Translation with Cross-Modal Alignment

1 code implementation25 Dec 2023 Rui Zhao, Liang Zhang, Biao Fu, Cong Hu, Jinsong Su, Yidong Chen

The first KL divergence optimizes the conditional variational autoencoder and regularizes the encoder outputs, while the second KL divergence performs a self-distillation from the posterior path to the prior path, ensuring the consistency of decoder outputs.

Decoder Sign Language Translation +1

Layer-wise Representation Fusion for Compositional Generalization

no code implementations20 Jul 2023 Yafang Zheng, Lei Lin, Shuangtao Li, Yuxuan Yuan, Zhaohong Lai, Shan Liu, Biao Fu, Yidong Chen, Xiaodong Shi

Inspired by this, we propose LRF, a novel \textbf{L}ayer-wise \textbf{R}epresentation \textbf{F}usion framework for CG, which learns to fuse previous layers' information back into the encoding and decoding process effectively through introducing a \emph{fuse-attention module} at each encoder and decoder layer.


Learning to Compose Representations of Different Encoder Layers towards Improving Compositional Generalization

no code implementations20 May 2023 Lei Lin, Shuangtao Li, Yafang Zheng, Biao Fu, Shan Liu, Yidong Chen, Xiaodong Shi

There is mounting evidence that one of the reasons hindering CG is the representation of the encoder uppermost layer is entangled, i. e., the syntactic and semantic representations of sequences are entangled.


Adapting Offline Speech Translation Models for Streaming with Future-Aware Distillation and Inference

1 code implementation14 Mar 2023 Biao Fu, Minpeng Liao, Kai Fan, Zhongqiang Huang, Boxing Chen, Yidong Chen, Xiaodong Shi

A popular approach to streaming speech translation is to employ a single offline model with a wait-k policy to support different latency requirements, which is simpler than training multiple online models with different latency constraints.

FAD Translation

CVT-SLR: Contrastive Visual-Textual Transformation for Sign Language Recognition with Variational Alignment

1 code implementation CVPR 2023 Jiangbin Zheng, Yile Wang, Cheng Tan, Siyuan Li, Ge Wang, Jun Xia, Yidong Chen, Stan Z. Li

In this work, we propose a novel contrastive visual-textual transformation for SLR, CVT-SLR, to fully explore the pretrained knowledge of both the visual and language modalities.

Sign Language Recognition

MOPRD: A multidisciplinary open peer review dataset

no code implementations9 Dec 2022 Jialiang Lin, Jiaxin Song, Zhangping Zhou, Yidong Chen, Xiaodong Shi

MOPRD is a strong endorsement for further studies in peer review-related research and other applications.

Comment Generation Review Generation

Towards Better Document-level Relation Extraction via Iterative Inference

1 code implementation26 Nov 2022 Liang Zhang, Jinsong Su, Yidong Chen, Zhongjian Miao, Zijun Min, Qingguo Hu, Xiaodong Shi

Existing methods usually directly predict the relations of all entity pairs of input document in a one-pass manner, ignoring the fact that predictions of some entity pairs heavily depend on the predicted results of other pairs.

Contrastive Learning Document-level Relation Extraction +1

Leveraging Graph-based Cross-modal Information Fusion for Neural Sign Language Translation

no code implementations1 Nov 2022 Jiangbin Zheng, Siyuan Li, Cheng Tan, Chong Wu, Yidong Chen, Stan Z. Li

Therefore, we propose to introduce additional word-level semantic knowledge of sign language linguistics to assist in improving current end-to-end neural SLT models.

Sign Language Translation Translation

Automatic Analysis of Available Source Code of Top Artificial Intelligence Conference Papers

no code implementations28 Sep 2022 Jialiang Lin, Yingmin Wang, Yao Yu, Yu Zhou, Yidong Chen, Xiaodong Shi

Some organizations and researchers manually collect AI papers with available source code to contribute to the AI community.

A Token-level Contrastive Framework for Sign Language Translation

1 code implementation11 Apr 2022 Biao Fu, PeiGen Ye, Liang Zhang, Pei Yu, Cong Hu, Yidong Chen, Xiaodong Shi

Sign Language Translation (SLT) is a promising technology to bridge the communication gap between the deaf and the hearing people.

Contrastive Learning Machine Translation +5

Computing Wasserstein-p Distance Between Images With Linear Cost

1 code implementation CVPR 2022 Yidong Chen, Chen Li, Zhonghua Lu

In this paper, we propose a novel algorithm to compute the Wasserstein-p distance between discrete measures by restricting the optimal transport (OT) problem on a subset.

Automated scholarly paper review: Concepts, technologies, and challenges

no code implementations15 Nov 2021 Jialiang Lin, Jiaxin Song, Zhangping Zhou, Yidong Chen, Xiaodong Shi

Peer review is a widely accepted mechanism for research evaluation, playing a pivotal role in academic publishing.

Logical Reasoning

Deep learning tackles single-cell analysis A survey of deep learning for scRNA-seq analysis

no code implementations25 Sep 2021 Mario Flores, Zhentao Liu, Ting-He Zhang, Md Musaddaqui Hasib, Yu-Chiao Chiu, Zhenqing Ye, Karla Paniagua, Sumin Jo, Jianqiu Zhang, Shou-Jiang Gao, Yu-Fang Jin, Yidong Chen, Yufei Huang

Here we present a processing pipeline of single-cell RNA-seq data, survey a total of 25 DL algorithms and their applicability for a specific step in the processing pipeline.

Generative Adversarial Network

Convolutional neural network models for cancer type prediction based on gene expression

1 code implementation18 Jun 2019 Milad Mostavi, Yu-Chiao Chiu, Yufei Huang, Yidong Chen

In breast cancer, for instance, our model identified well-known markers, such as GATA3 and ESR1.

Type prediction

Asynchronous "Events" are Better For Motion Estimation

no code implementations24 Apr 2019 Yuhu Guo, Han Xiao, Yidong Chen, Xiaodong Shi

As an instance of event-based camera, Dynamic and Active-pixel Vision Sensor (DAVIS) combines a standard camera and an event-based camera.

Motion Estimation

GSAE: an autoencoder with embedded gene-set nodes for genomics functional characterization

no code implementations21 May 2018 Hung-I Harry Chen, Yu-Chiao Chiu, Tinghe Zhang, Songyao Zhang, Yufei Huang, Yidong Chen

We introduced the concept of the gene superset, an unbiased combination of gene sets with weights trained by the autoencoder, where each node in the latent layer is a superset.

Survival Analysis

Predicting drug response of tumors from integrated genomic profiles by deep neural networks

1 code implementation20 May 2018 Yu-Chiao Chiu, Hung-I Harry Chen, Tinghe Zhang, Songyao Zhang, Aparna Gorthi, Li-Ju Wang, Yufei Huang, Yidong Chen

We trained and tested the model on a dataset of 622 cancer cell lines and achieved an overall prediction performance of mean squared error at 1. 96 (log-scale IC50 values).

Hungarian Layer: Logics Empowered Neural Architecture

no code implementations7 Dec 2017 Han Xiao, Yidong Chen, Xiaodong Shi

However, lacking of logic flow (e. g. \textit{if, for, while}), traditional algorithms (e. g. \textit{Hungarian algorithm, A$^*$ searching, decision tress algorithm}) could not be embedded into this paradigm, which limits the theories and applications.


Deep Semantic Role Labeling with Self-Attention

1 code implementation5 Dec 2017 Zhixing Tan, Mingxuan Wang, Jun Xie, Yidong Chen, Xiaodong Shi

Semantic Role Labeling (SRL) is believed to be a crucial step towards natural language understanding and has been widely studied.

Natural Language Understanding Semantic Role Labeling

XMU Neural Machine Translation Systems for WAT 2017

no code implementations WS 2017 Boli Wang, Zhixing Tan, Jinming Hu, Yidong Chen, Xiaodong Shi

This paper describes the Neural Machine Translation systems of Xiamen University for the shared translation tasks of WAT 2017.

Decoder Machine Translation +2

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