Search Results for author:
Found 34 papers, 12 papers with code
Improving Implicit Discourse Relation Recognition with Discourse-specific Word Embeddings
We introduce a simple and effective method to learn discourse-specific word embeddings (DSWE) for implicit discourse relation recognition.
XMU Neural Machine Translation Systems for WAT 2017
This paper describes the Neural Machine Translation systems of Xiamen University for the shared translation tasks of WAT 2017.
XMU Neural Machine Translation Online Service
We demonstrate a neural machine translation web service.
Deep Semantic Role Labeling with Self-Attention
Semantic Role Labeling (SRL) is believed to be a crucial step towards natural language understanding and has been widely studied.
Ranked #14 on
Semantic Role Labeling
on OntoNotes
Hungarian Layer: Logics Empowered Neural Architecture
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.
Predicting drug response of tumors from integrated genomic profiles by deep neural networks
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).
GSAE: an autoencoder with embedded gene-set nodes for genomics functional characterization
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.
Asynchronous "Events" are Better For Motion Estimation
As an instance of event-based camera, Dynamic and Active-pixel Vision Sensor (DAVIS) combines a standard camera and an event-based camera.
Convolutional neural network models for cancer type prediction based on gene expression
In breast cancer, for instance, our model identified well-known markers, such as GATA3 and ESR1.
A Document-Level Neural Machine Translation Model with Dynamic Caching Guided by Theme-Rheme Information
Research on document-level Neural Machine Translation (NMT) models has attracted increasing attention in recent years.
Deep learning tackles single-cell analysis A survey of deep learning for scRNA-seq analysis
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.
Automated scholarly paper review: Concepts, technologies, and challenges
Peer review is a widely accepted mechanism for research evaluation, playing a pivotal role in academic publishing.
Computing Wasserstein-p Distance Between Images With Linear Cost
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.
A Token-level Contrastive Framework for Sign Language Translation
Sign Language Translation (SLT) is a promising technology to bridge the communication gap between the deaf and the hearing people.
Ranked #6 on
Sign Language Translation
on CSL-Daily
Automatic Analysis of Available Source Code of Top Artificial Intelligence Conference Papers
Some organizations and researchers manually collect AI papers with available source code to contribute to the AI community.
Leveraging Graph-based Cross-modal Information Fusion for Neural Sign Language Translation
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.
Towards Better Document-level Relation Extraction via Iterative Inference
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.
MOPRD: A multidisciplinary open peer review dataset
MOPRD is a strong endorsement for further studies in peer review-related research and other applications.
CVT-SLR: Contrastive Visual-Textual Transformation for Sign Language Recognition with Variational Alignment
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.
Adapting Offline Speech Translation Models for Streaming with Future-Aware Distillation and Inference
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.
Learning to Compose Representations of Different Encoder Layers towards Improving Compositional Generalization
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.
Layer-wise Representation Fusion for Compositional Generalization
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.
Conditional Variational Autoencoder for Sign Language Translation with Cross-Modal Alignment
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.
XMU’s Simultaneous Translation System at NAACL 2021
This paper describes our two systems submitted to the simultaneous translation evaluation at the 2nd automatic simultaneous translation workshop.
Towards Robust Neural Machine Translation with Iterative Scheduled Data-Switch Training
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.
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)
“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。”
