联系方式
Contact Information
团队简介
Team Introduction
天津大学自然语言处理团队（TJUNLP）研究方向包括机器翻译、问答、对话、自然语言生成、社交媒体分析、大规模预训练模型、多模态学习、认知启发的自然语言处理、常识推理、智慧医疗等，近年来主持和参与了多项国家级项目和国际合作项目，包括自然科学基金重点项目、优青项目、英国皇家学会牛顿高级学者基金项目、科技部政府间国际科技创新合作重点专项等。发表论文100余篇，其中CCF A/B类国际会议（ACL、AAAI、IJCAI等）和期刊论文（AI、 IEEE TPAMI、Information Sciences、IEEE TASLP等）50余篇，Springer出版全英文专著1部。研究成果获得北京市科学技术二等奖、钱伟长中文信息处理科学技术奖等奖项。
TJUNLP具有良好的科研氛围、充足的科研经费。目前已与世界上多个知名大学自然语言实验室开展深入合作， 包括英国爱丁堡大学、葡萄牙里斯本大学、西班牙巴斯克大学等，与相关知名研究机构共建天津市“一带一路”联合实验室（天津大学“语言智能与技术”中外联合研究中心）；与国内外多家企业开展了联合研究与技术攻关， 如华为、联想、OPPO、今日头条等，并与相关企业建立了校企联合实验室。实验室常年接受海内外学生实习和访问交流， 同时选送优秀学生赴国外大学和国内知名企业实习与交流合作。
更多信息：https://tjunlp-lab.github.io
团队负责人：熊德意
天津大学智能与计算学部教授、博士生导师、自然语言处理实验室负责人，天津大学“语言智能与技术”中外联合研究中心主任。主要研究方向为自然语言处理，特别专注于机器翻译、对话、问答、自然语言生成、常识推理、认知计算、智慧医疗等方向的研究。在Computational Linguistics、IEEE TPAMI、AI、AAAI、ACL等国际著名期刊和会议上发表论文100余篇，Springer出版英文专著一部。获得国家自然科学基金优秀青年科学基金、国家重点研发计划“政府间国际科技合作创新合作”重点专项、英国皇家学会牛顿高级学者基金等资助。获得新加坡资讯通信研究院2008年年度研究贡献奖、北京市科学技术奖二等奖、中文信息学会“钱伟长中文信息处理科学技术奖-汉王青年创新奖”一等奖等奖项。曾是亚洲自然语言处理联合会AFNLP干事、新加坡中文与东方语文信息处理学会理事会成员，目前是中国中文信息学会理事。担任IALP 2012&2021程序委员会共同主席，CWMT 2017程序委员会共同主席，欧盟多国联合项目QTLeap咨询专家，ACL、EMNLP、NAACL、COLING等多个知名国际会议领域主席，以及TACL和ARR的Action Editor等。
更多信息：http://cic.tju.edu.cn/faculty/xiongdeyi/index.html
TJUNLP专注于自然语言处理（NLP）研究，具体包括NLP底层基础理论体系（如篇章理论与分析）、NLP关键资源库、NLP核心技术（机器翻译、对话、机器阅读理解与问答、自然语言生成等）以及NLP技术转化与产业应用等方面的研究，另外团队也开展自然语言处理与神经语言学、脑科学等交叉学科方向的研究。
近年来主持和参与了多项国家级项目和国际合作项目，包括自然科学基金优秀青年科学基金、英国皇家学会牛顿高级学者基金、科技部政府间国际科技创新合作重点专项、科技部重点研发计划课题、天津市自然科学基金重点基金等。同时，实验室与多个知名企业开展了多项横向项目的合作研究。
近三年论文发表情况：
2021
Erguang Yang, Mingtong Liu, Deyi Xiong, YUJIE ZHANG, Yao Meng, Changjian Hu, Jinan Xu and Yufeng Chen. Syntactically-Informed UnsupervisedParaphrasing with Non-Parallel Data. Accepted by EMNLP2021.
Huibin Ge, Chenxi Sun, Deyi Xiong and Qun Liu. Chinese WPLC: A Chinese Dataset for Evaluating Pretrained Language Models on Word Prediction Given Long-Range Context. Accepted by EMNLP2021.
Jiachen Tian, Shizhan Chen, Xiaowang Zhang, Zhiyong Feng, Deyi Xiong, Shaojuan Wu and Chunliu Dou. Difficult Samples Re-embedding via Mutual Information Constrained Semantically Oversampling. Accepted by EMNLP2021.
Hongfei Xu, Qiuhui Liu, Josef van Genabith and Deyi Xiong. Learning Hard Retrieval Decoder Attention for Transformers. Accepted by Findings of EMNLP 2021.
Tao Wang, Chengqi Zhao, Mingxuan Wang, Lei Li, Hang Li, Deyi Xiong. Secoco: Self-Correcting Encoding for Neural Machine Translation. Accepted by Findings of EMNLP 2021.
Shiqi Zhang, Yan Liu, Deyi Xiong, Pei Zhang, Boxing Chen. Domain-Aware Self-Attention for Multi-Domain Neural Machine Translation. Accepted by INTERSPEECH2021.
Yuqi Ren and Deyi Xiong. CogAlign: Learning to Align Textual Neural Representations to Cognitive Signals. Accepted by ACL 2021.
Jie He, Bo Peng, Yi Liao, Qun Liu and Deyi Xiong. TGError: An Error-Annotated Dataset and Benchmark Tasks for Text Generation from Pretrained Language Models. Accepted by ACL 2021.
Hongfei Xu, Qiuhui Liu, Josef van Genabith, Deyi Xiong and Meng Zhang. Multi-Head Highly Parallelized LSTM Decoder for Neural Machine Translation. Accepted by ACL 2021.
Hongfei Xu, Qiuhui Liu, Josef van Genabith and Deyi Xiong. Modeling Task-Aware MIMO Cardinality for Efficient Multilingual Neural Machine Translation. Accepted by ACL 2021.
Zhiyuan Zeng and Deyi Xiong. An Empirical Study on Adversarial Attack on NMT: Languages and Positions Matter. Accepted by ACL 2021.
Kaiyu Huang, Junpeng Liu, Degen Huang, Deyi Xiong, Zhuang Liu and Jinsong Su. Exploiting Chinese Word Segmentation via Pseudo Labels for Practicability. Accepted by Findings of ACL 2021.
Wuwei Huang, Dexin Wang and Deyi Xiong. AdaST: Dynamically Adapting Encoder States in the Decoder forEnd-to-End Speech-to-Text Translation. Accepted by Findings of ACL 2021.
Dexin Wang and Deyi Xiong. Efficient Object-Level Visual Context Modeling for Multimodal Machine Translation: Masking Irrelevant Objects Helps Grounding. Accepted by AAAI 2021.
Jun Quan, Meng Yang, Qiang Gan, Deyi Xiong et. al. Integrating Pre-trained Models into Rule-based Dialogue Management. Accepted by AAAI 2021.
Hongfei Xu, Josef van Genabith, Qiuhui Liu, Deyi Xiong. Probing Word Translations in the Transformer and Trading Decoder for Encoder Layers. Accepted by NAACL 2021.
Tao Wang, Chengqi Zhao, Mingxuan Wang, Lei Li and Deyi Xiong. Auto Correcting in the Process of Translation --- Multi-task Learning Improves Dialogue Machine Translation. Accepted by NAACL 2021.
Wenjie Qin, Xiang Li, Yuhui Sun, Deyi Xiong, Jianwei Cui, Bin Wang. Modeling Homophone Noise for Robust Neural Machine Translation. Accepted by ICASSP 2021.
Jinsong Su, Jialong Tang, Hui Jiang, Ziyao Lu, Yubin Ge, Linfeng Song, Deyi Xiong, Le Sun, Jiebo Luo. Enhanced aspect-based sentiment analysis models with progressive self-supervised attention learning. Accepted by Artificial Intelligence. 2021.
2020
Xu Cao, Deyi Xiong, Chongyang Shi, Chao Wang, Yao Meng and Changjian Hu. Balanced Joint Adversarial Training for Robust Intent Detection and Slot Filling. Accepted by COLING 2020.
Mingtong Liu, Erguang Yang, Deyi Xiong, Yujie Zhang, Yao Meng, Changjian Hu, Jinan Xu and Yufeng Chen. A Learning-Exploring Method to Generate Diverse Paraphrases with Multi-Objective Deep Reinforcement Learning. Accepted by COLING 2020.
Yufang Huang, Wentao Zhu, Deyi Xiong, Yiye Zhang, Changjian Hu and Feiyu Xu. Cycle-Consistent Adversarial Autoencoders for Unsupervised Text Style Transfer. Accepted by COLING 2020.
Jun Quan, Shian Zhang, Qian Cao, Zizhong Li, and Deyi Xiong. RiSAWOZ: A Large-Scale Multi-Domain Wizard-of-Oz Dataset with Rich Semantic Annotations for Task-Oriented Dialogue Modeling. Accepted by EMNLP 2020.
Wanqiu Long, Bonnie Webber and Deyi Xiong. TED-CDB: A Large-Scale Chinese Discourse Relation Dataset on TED Talks. Accepted by EMNLP 2020.
Jie He, Tao Wang, Deyi Xiong and Qun Liu. The Box is in the Pen: Evaluating Commonsense Reasoning in Neural Machine Translation. Accepted by Findings of EMNLP 2020.
Hongfei Xu, Josef van Genabith, Deyi Xiong, Qiuhui Liu, Jingyi Zhang. Learning Source Phrase Representations for Neural Machine Translation. Accepted by ACL 2020.
Hongfei Xu, Qiuhui Liu, Josef van Genabith, Deyi Xiong, Jingyi Zhang. Lipschitz Constrained Parameter Initialization for Deep Transformers. Accepted by ACL 2020.
Hongfei Xu, Josef van Genabith, Deyi Xiong, Qiuhui Liu. Dynamically Adjusting Transformer Batch Size by Monitoring Gradient Direction Change. Accepted by ACL 2020.
Jun Quan and Deyi Xiong. Modeling Long Context for Task-Oriented Dialogue State Generation. Accepted by ACL 2020.
Hongfei Xu, Josef van Genabith, Deyi Xiong, Qiuhui Liu. Efficient Context-Aware Neural Machine Translation with Layer-Wise Weighting and Input-Aware Gating. Accepted by IJCAI- PRICAI 2020.
Mingtong Liu, Erguang Yang, Deyi Xiong, Yujie Zhang, Chen Sheng, Changjian Hu, Jinan Xu, Yufeng Chen. Exploring Bilingual Parallel Corpora for Syntactically Controllable Paraphrase Generation. Accepted by IJCAI- PRICAI 2020.
Biao Zhang, Deyi Xiong, Jun Xie, Jinsong Su. Neural Machine Translation With GRU-Gated Attention Model. Accepted by IEEE Transactions on Neural Networks and Learning Systems. 2020. DOI: 10.1109/TNNLS.2019.2957276. [pdf]
Qian Cao, Shaohui Kuang and Deyi Xiong. Learning to Reuse Translations: Guiding Neural Machine Translation with Examples. Accepted by ECAI 2020. [pdf]
Pei Zhang, Xu Zhang, Wei Chen, Jian Yu, Yanfeng Wang and Deyi Xiong. Learning Contextualized Sentence Representations for Document-Level Neural Machine Translation. Accepted by ECAI 2020.
Wanqiu Long, Xinyi Cai, James E.M.Reid, Bonnie Webber and Deyi Xiong. Shallow Discourse Annotation for Chinese TED Talks. Accepted by LREC 2020. [pdf] [dataset]
2019
Jiazuo Qiu, Deyi Xiong. "Generating Highly Relevant Questions" Accepted by EMNLP 2019. [pdf]
Jun Quan, Deyi Xiong, Bonnie Webber and Changjian Hu. "GECOR: An End-to-End Generative Ellipsis and Co-reference Resolution Model for Task-Oriented Dialogue" Accepted by EMNLP 2019. Long Paper. [pdf]
Jun Quan, Deyi Xiong. "Effective Data Augmentation Approaches to End-to-End Task-Oriented Dialogue" Accepted by IALP 2019. [pdf]
Yimin Jing, Deyi Xiong, Yan Zhen "BiPaR: A Bilingual Parallel Dataset for Multilingual and Cross-lingual Reading Comprehension on Novels" Accepted as a long paper at EMNLP 2019 [pdf] [code]
Xin Tan, Longyin Zhang, Deyi Xiong and Guodong Zhou. "Hierarchical Modeling of Global Context for Document-Level Neural Machine Translation" Accepted by EMNLP 2019. [pdf]
Xin Tan, Shaohui Kuang, Deyi Xiong "Detecting and Translating Dropped Pronouns in Neural Machine Translation" Accepted by NLPCC 2019. [pdf]
Biao Zhang, Deyi Xiong, Jinsong Su, Jiebo Luo "Future-Aware Knowledge Distillation for Neural Machine Translation" Accepted by IEEE/ACM Transactions on Audio, Speech, and Language Processing 2019. [pdf]
Rodrigo Pereira dos Santos, João M. N. Silva, António Branco, Deyi Xiong "The Direct Path May Not Be The Best: Portuguese-Chinese Neural Machine Translation" Accepted by EPIA 2019.
天津大学研究生院招生办公室
文件上传中...
