已发表成果:
WOK 论文 115 篇;中文核心 19 篇;其它论文 9 篇;专利发明 2 个;
FT-GAN: Fine-Grained Tune Modeling for Chinese Opera Synthesis
Layer-Wise Representation Fusion for Compositional Generalization
CDSKNN<SUP>XMBD</SUP>: a novel clustering framework for large-scale single-cell data based on a stable graph structure
UniMem: Towards a Unified View of Long-Context Large Language Models
Improving few-shot relation extraction through semantics-guided learning
A multitask co-training framework for improving speech translation by leveraging speech recognition and machine translation tasks
AN EXPLICIT MULTI-MODAL FUSION METHOD FOR SIGN LANGUAGE TRANSLATION
MEMORY-AUGMENTED SPEECH-TO-TEXT TRANSLATION WITH MULTI-SCALE CONTEXT TRANSLATION STRATEGY
Adaptive Simultaneous Sign Language Translation with Confident Translation Length Estimation
Signer Diversity-driven Data Augmentation for Signer-Independent Sign Language Translation
Automatic Reference-Free Fine-Grained Machine Translation Error Detection via Named Entity Recognition and Back-Translation
Automated scholarly paper review: Concepts, technologies, and challenges
How many preprints have actually been printed and why: a case study of computer science preprints on arXiv
Layer-wise Representation Fusion for Compositional Generalization
Exploring Self-Distillation Based Relational Reasoning Training for Document-Level Relation Extraction
Learn to Compose Syntactic and Semantic Representations Appropriately for Compositional Generalization
LEAPT: LEARNING ADAPTIVE PREFIX-TO-PREFIX TRANSLATION FOR SIMULTANEOUS MACHINE TRANSLATION
Adapting Offline Speech Translation Models for Streaming with Future-Aware Distillation and Inference
A High-Quality Melody-Aware Peking Opera Synthesizer Using Data Augmentation
MOPRD: A multidisciplinary open peer review dataset
Consistent Prototype Learning for Few-Shot Continual Relation Extraction
COSYWA: Enhancing Semantic Integrity in?Watermarking Natural Language Generation
A Novel POS-Guided Data Augmentation Method for?Sign Language Gloss Translation
A Compact Phoneme-To-Audio Aligner for?Singing Voice
A Token-Level Contrastive Framework for Sign Language Translation
LEAPT: Learning Adaptive Prefix-to-Prefix Translation For Simultaneous Machine Translation
MOPRD: A multidisciplinary open peer review dataset
Towards Better Document-level Relation Extraction via Iterative Inference
Detecting and analyzing missing citations to published scientific entities
Automatic Analysis of Available Source Code of Top Artificial Intelligence Conference Papers
A downsampling method enables robust clustering and integration of single-cell transcriptome data
Detecting and analyzing missing citations to published scientific entities
ConSLT: A Token-level Contrastive Framework for Sign Language Translation
Continuous Prompt Enhanced Biomedical Entity Normalization
FCH-TTS: Fast, Controllable and High-quality Non-Autoregressive Text-to-Speech Synthesis
Automatic Analysis of Available Source Code of Top Artificial Intelligence Conference Papers
Adversarial Soft Prompt Tuning for Cross-Domain Sentiment Analysis
Towards Better Document-level Relation Extraction via Iterative Inference
Enhancing Neural Sign Language Translation by highlighting the facial expression information
Knowledge Graph Embedding Based on Multi-View Clustering Framework
Synchronous Dual Network with Cross-Type Attention for Joint Entity and Relation Extraction
CTRD: A Chinese Theme-Rheme Discourse Dataset
A Document-Level Machine Translation Quality Estimation Model Based on Centering Theory
Generating Diverse Back-Translations via Constraint Random Decoding
A Chinese Main Location Extraction Method based on IDLSTM+CRF
A Multi-Task Approach for Improving Biomedical Named Entity Recognition by Incorporating Multi-Granularity Information
XMU’s Simultaneous Translation System at NAACL 2021
How many preprints have actually been printed and why: a case study of computer science preprints on arXiv
An Improved Sign Language Translation Model with Explainable Adaptations for Processing Long Sign Sentences
A Document-Level Neural Machine Translation Model with Dynamic Caching Guided by Theme-Rheme Information
Phrase-Based Tibetan-Chinese Statistical Machine Translation
Multi-perspective neural architecture for recommendation system
Technical Approaches to Chinese Sign Language Processing: A Review
Boosting implicit discourse relation recognition with connective-based word embeddings
Constructing and validating word similarity datasets by integrating methods from psychology, brain science and computational linguistics
A microblog dataset for Tibetan sentiment analysis
Deep semantic role labeling with self-attention
XMU neural machine translation systems for WAT2018 Myanmar-english translation task
Deriving Probabilistic Semantic Frames from HowNet
Lattice-to-sequence attentional Neural Machine Translation models
A Multidisciplinary Method for Constructing and Validating Word Similarity Datasets
A Sentence Segmentation Method for Ancient Chinese Texts Based on Recurrent Neural Network
Co-training for Implicit Discourse Relation Recognition Based on Manual and Distributed Features
XMU neural machine translation systems for WMT 17
XMU Neural Machine Translation Systems for WAT 2017
XMU Neural Machine Translation Online Service
Lattice-based recurrent neural network encoders for neural machine translation
Improving implicit discourse relation recognition with discourse-specific word embeddings
A synergetic semantic role labeling model with the introduction of fluctuating force accompanied with word sense information
Leveraging bilingually-constrained synthetic data via multi-task neural networks for implicit discourse relation recognition
Adapted competitive learning on continuous semantic space for word sense induction
Coping with problems of unicoded traditional Mongolian
A sense embedding of deep convolutional neural networks for sentiment classification
Bilingually-constrained Synthetic Data for Implicit Discourse Relation Recognition
An SNN-Based Semantic Role Labeling Model with Its Network Parameters Optimized Using an Improved PSO Algorithm
Recursive autoencoder based automatic features learning for implicit discourse relations recognition
Sentiment analysis via integrating distributed representations of variable-length word sequence
Unsupervised word sense induction using rival penalized competitive learning
Intelligent cloud learning model for online overseas Chinese education
Cross-lingual tense tagging based on markov tree tagging model
Global reoccurrence measure for keyword extraction
Improved statistical machine translation model with topic-based paraphrase
Topic-aware pivot language approach for statisticalmachine translation
On-going Cooperative Research towards Developing Economy-Oriented Chinese-French SMT Systems with a New SMT Framework
Pivot probability induction for statistical machine translation with topic similarity
Automated extraction of lexicon applied both to chinese and japanese corpora
A novel word sense disambiguation algorithm based on semi-supervised statistical learning
A parallel SRL algorithm based on synergetic neural network
Translation model adaptation for statistical machine translation with monolingual topic information
An approach to n-gram language model evaluation in phrase-based statistical machine translation
A Method for Incorporating Language Models Based on Linkage Grammar into Phrase-Based SMT Models
A simplified-traditional Chinese character conversion model based on log-linear models
Automatic partition of chinese sentence group
Improving phrase-based statistical machine translation models by incorporating syntax-based language models
A distributed parallel AdaBoost algorithm for face detection
METAPHOR RECOGNITION: CHMETA, A PATTERN-BASED SYSTEM
A word alignment model based on multiobjective evolutionary algorithms
The China-brain project report on the first six months
Automatic acquisition of phrase semantic rule for Chinese
Incorporating syntax-based language models in phrase-based SMT models
New word detection algorithm for Chinese based on extraction of local context information
A chunk-based reordering model for phrase-based SMT systems
Dependency-based Chinese-English statistical machine translation
Translation memory sharing models in XMCAT
A VoIP client system framework and its implementation
Automatic Keyphrase Extraction from Chinese books
Nbest dependency parsing with linguistically rich models
The XMU SMT System for IWSLT 2007
The XMU Phrase-Based Statistical Machine Translation System for IWSLT 2006
A message filtering system in pervasive computing
Towards a multilingual, multimedia and multimodal digital library platform
A model for ranking sentence pairs in parallel corpora
Automatic extraction of Chinese terms
多策略汉英平行语料的过滤方法研究
厦门大学学报(自然科学版),0438-0479,2021-06-21.通过标点恢复提高机器同传效果
计算机应用,1001-9081,2020-01-15.通过标点恢复提高机器同传效果
计算机应用,1001-9081,2020-01-15.短文本情感分析的研究现状——从社交媒体到资源稀缺语言
计算机科学,1002-137X,2018.一种基于循环神经网络的古文断句方法
北京大学学报. 自然科学版,0479-8023,2017.一种基于循环神经网络的古文断句方法
北京大学学报(自然科学版),0479-8023,2016-11-30.基于特征自动选择方法的汉语隐喻计算
厦门大学学报(自然科学版),0438-0479,2016-04-11.基于树形条件随机场的跨语言时态标注
软件学报,1000-9825,2015-12-15.基于复述技术的汉语成语翻译方法研究
中文信息学报,1003-0077,2015-07-15.语料库语言学视角下的台湾汉字简化研究
北京大学学报(自然科学版),0479-8023,2014-11-28.古典诗词动画自动生成研究
北京大学学报(自然科学版),0479-8023,2014-11-28.引入基于主题复述知识的统计机器翻译模型
浙江大学学报(工学版),1008-973X,2014-10-15.引入集成学习的最大熵短语调序模型
中文信息学报,1003-0077,2014-01-15.引入复述技术的统计机器翻译研究综述
智能系统学报,1673-4785,2013-05-15.基于话题分布相似度的无监督评论词消歧方法
北京大学学报(自然科学版),0479-8023,2012-10-26.央金藏文分词系统
中文信息学报,1003-0077,2011.基于HTK的语音识别的并行化研究与实现
计算机应用 ,1001-9081 ,2009.潜在语义分析在连续语音识别中的应用
计算机工程与应用 ,1002-8331 ,2009.利用FP-树构造多词Trigger对语言模型
厦门大学学报(自然科学版),0438-0479,2005-12-30.中文问答系统中答案抽取的研究
电脑知识与技术,1009-3044,2011.利用人类计算技术的语音语料库标注方法及其实现
智能系统学报 ,1673-4785 ,2009.基于HMM的汉语整句拼音输入法研究
现代计算机(专业版),1007-1423,2008-04-25.手机短消息过滤系统的研究与实现
黑龙江科技信息,1673-1328,2007-07-08.2005统计机器翻译研讨班研究报告
中文信息学报,1003-0077,2006-09-30.一个统计与规则相结合的中文命名实体识别系统
计算机应用,1001-9081,2005-10-10.一种基于提取上下文信息的分词算法
计算机应用,1001-9081,2005-09-10.基于模板的机器翻译系统中模板库的自动构建技术
计算机应用,1001-9081,2004-09-28.机器翻译测评的实践与分析
计算机应用研究,1001-3695,2004-03-28.