Xu SUN

Selected publications


2020

  1. Visual Agreement Regularized Training for Multi-Modal Machine Translation
    Pengcheng Yang, Pei Zhang, Boxing Chen, Xu Sun*
    AAAI 2020

  2. Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View
    Deli Chen, Yankai Lin, Wei Li, Peng Li, Jie Zhou, Xu Sun*
    AAAI 2020

2019

  1. Understanding and Improving Layer Normalization
    Jingjing Xu, Xu Sun*, Zhiyuan Zhang, Guangxiang Zhao, Junyang Lin
    NeurIPS 2019
    [pdf] [poster]

  2. Aligning Visual Regions and Textual Concepts for Semantic-Grounded Image Representations
    Fenglin Liu#, Yuanxin Liu#, Xuancheng Ren#, Xiaodong He, Xu Sun*
    NeurIPS 2019
    [pdf] [poster]

  3. Key Fact as Pivot: A Two-Stage Model for Low Resource Table-to-Text Generation
    Shuming Ma, Pengcheng Yang, Tianyu Liu, Peng Li, Jie Zhou and Xu Sun*
    ACL 2019
    [pdf] [bibtex]

  4. Coherent Comments Generation for Chinese Articles with a Graph-to-Sequence Model
    Wei Li, Jingjing Xu, Yancheng He, ShengLi Yan, Yunfang Wu and Xu Sun*
    ACL 2019
    [pdf] [bibtex]

  5. Imitation Learning for Non-Autoregressive Neural Machine Translation
    Bingzhen Wei, Mingxuan Wang, Hao Zhou, Junyang Lin and Xu Sun*
    ACL 2019
    [pdf] [bibtex]

  6. A Hierarchical Reinforced Sequence Operation Method for Unsupervised Text Style Transfer
    Chen Wu#, Xuancheng Ren#, Fuli Luo, Xu Sun*
    ACL 2019
    [pdf] [bibtex]

  7. Enhancing Topic-to-Essay Generation with External Commonsense Knowledge
    Pengcheng Yang#, Lei Li#, Fuli Luo, Tianyu Liu and Xu Sun*
    ACL 2019
    [pdf] [bibtex]

  8. Towards Fine-grained Text Sentiment Transfer
    Fuli Luo, Peng Li, Pengcheng Yang, Jie Zhou, Yutong Tan, Baobao Chang, Zhifang Sui and Xu Sun
    ACL 2019
    [pdf] [bibtex]

  9. Adaptive Gradient Methods with Dynamic Bound of Learning Rate.
    Liangchen Luo#, Yuanhao Xiong#, Yan Liu, Xu Sun*.
    ICLR 2019
    [pdf][code] [bibtex]

  10. Asking Clarification Questions in Knowledge-Based Question Answering
    Jingjing Xu, Yuechen Wang, Duyu Tang, Nan Duan, Pengcheng Yang, Qi Zeng, Ming Zhou, Xu Sun*
    EMNLP 2019
    [pdf]

  11. Lexical-Based Adversarial Reinforcement Training for Robust Sentiment Classification
    Jingjing Xu, Liang Zhao, Hanqi Yan, Qi Zeng, Yun Liang, Xu Sun*
    EMNLP 2019
    [pdf]

  12. Aligning Cross-Lingual Entities with Multi-Aspect Information
    Hsiu-Wei Yang, Yanyan Zou, Peng Shi, Wei Lu, Jimmy Lin, Xu Sun
    EMNLP 2019
    [pdf]

  13. Exploring and Distilling Cross-Modal Information for Image Captioning
    Fenglin Liu#, Xuancheng Ren#, Yuanxin Liu, Kai Lei*, Xu Sun*
    IJCAI 2019
    [pdf] [bibtex]

  14. Knowledgeable Storyteller: A Commonsense-Driven Generative Model for Visual Storytelling
    Pengcheng Yang, Fuli Luo, Peng Chen, Lei Li, Xiaodong He and Xu Sun*
    IJCAI 2019
    [pdf] [bibtex]

  15. A Dual Reinforcement Learning Framework for Unsupervised Text Style Transfer
    Fuli Luo, Peng Li, Jie Zhou, Pengcheng Yang, Baobao Chang, Zhifang Sui, Xu Sun
    IJCAI 2019
    [pdf] [bibtex]

  16. Training Simplification and Model Simplification for Deep Learning: A Minimal Effort Back Propagation Method.
    Xu Sun*#, Xuancheng Ren#, Shuming Ma, Bingzhen Wei, Wei Li, Jingjing Xu, Houfeng Wang, Yi Zhang.
    IEEE Transactions on Knowledge and Data Engineering (TKDE) 2019
    [doi][code]

  17. Towards Easier and Faster Sequence Labeling for Natural Language Processing: A Search-based Probabilistic Online Learning Framework (SAPO).
    Xu Sun*, Shuming Ma, Yi Zhang, Xuancheng Ren.
    Information Sciences. Elsevier. 478:303-317, 2019
    [doi][code]

  18. LiveBot: Generating Live Video Comments Based on Visual and Textual Contexts.
    Shuming Ma, Lei Cui, Damai Dai, Furu Wei, Xu Sun*.
    AAAI 2019
    [pdf][bibtex] [code]

  19. Learning Personalized End-to-End Goal-Oriented Dialog
    Liangchen Luo, Wenhao Huang, Qi Zeng, Zaiqing Nie, Xu Sun*.
    AAAI 2019
    [pdf][bibtex]

2018

  1. Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approach.
    Jingjing Xu, Xu Sun*,Qi Zeng, Xiaodong Zhang, Xuancheng Ren, Houfeng Wang, Wenjie Li.
    ACL 2018
    [pdf][code] [bibtex][ppt]

  2. Question Condensing Networks for Answer Selection in Community Question Answering.
    Wei Wu, Xu Sun, Houfeng Wang.
    ACL 2018
    [pdf][bibtex]

  3. Autoencoder as Assistant Supervisor: Improving Text Representation for Chinese Social Media Text Summarization.
    Shuming Ma, Xu Sun*, Junyang Lin, Houfeng Wang.
    ACL 2018
    [pdf][code] [bibtex][ppt]

  4. Bag-of-Words as Target for Neural Machine Translation.
    Shuming Ma, Xu Sun*, Yizhong Wang, Junyang Lin.
    ACL 2018
    [pdf][code] [bibtex][ppt]

  5. Global Encoding for Abstractive Summarization.
    Junyang Lin, Xu Sun*, Shuming Ma, Qi Su.
    ACL 2018
    [pdf][code] [bibtex][ppt]

  6. SGM: Sequence Generation Model for Multi-label Classification
    Pengcheng Yang, Xu Sun*, Wei Li, Shuming Ma, Wei Wu, Houfeng Wang
    COLING 2018 (Best Paper Award[link])
    [pdf][code] [bibtex][ppt]

  7. Does Higher Order LSTM Have Better Accuracy for Segmenting and Labeling Sequence Data?
    Yi Zhang, Xu Sun*, Shuming Ma, Yang Yang, Xuancheng Ren
    COLING 2018
    [pdf][code] [bibtex][ppt]

  8. Deconvolution-Based Global Decoding for Neural Machine Translation
    Junyang Lin, Xu Sun*, Xuancheng Ren, Shuming Ma, Jinsong Su, Qi Su
    COLING 2018
    [pdf][code] [bibtex][ppt]

  9. An End-to-End Question Answering Model Based on Semi-Structured Tables
    Hao Wang, Xiaodong Zhang, Shuming Ma, Xu Sun, Houfeng Wang
    COLING 2018

  10. Cross-Domain and Semi-Supervised Named Entity Recognition in Chinese Social Media: A Unified Model
    Jingjing Xu, Hangfeng He, Xuancheng Ren, Sujian Li, Xu Sun*
    IEEE Transactions on Audio, Speech and Language Processing (TASLP) 26: 2142-2152, 2018
    [doi][code]

  11. DP-GAN: A Diversity-Promoting Generative Adversarial Network for Generating Informative and Diversified Text
    Jingjing Xu, Xuancheng Ren, Junyang Lin, Xu Sun*
    EMNLP 2018
    [pdf][code] [bibtex][ppt]

  12. Stepwise Image-Topic Merging Network for Generating Detailed and Comprehensive Image Captions
    Fenglin Liu#, Xuancheng Ren#, Yuanxin Liu, Houfeng Wang, Xu Sun*
    EMNLP 2018
    [pdf][code] [bibtex][ppt]

  13. A Skeleton-Based Model for Promoting Coherence Among Sentences in Narrative Story Generation
    Jingjing Xu, Xuancheng Ren, Yi Zhang, Qi Zeng, Xiaoyan Cai, Xu Sun*
    EMNLP 2018
    [pdf][code] [bibtex][ppt]

  14. Labeling Dialogue Data with Unsupervised Learning
    C. Shi, Q. Che, L. Sha, S. Li, X. Sun, H. Wang, T. Lin
    EMNLP 2018

  15. A Hierarchical End-to-End Model for Jointly Improving Text Summarization and Sentiment Classification.
    Shuming Ma, Xu Sun*, Junyang Lin, Xuancheng Ren.
    IJCAI 2018
    [pdf][bibtex] [ppt]

  16. Duplicate Question Identification by Integrating FrameNet with Neural Networks.
    Xiaodong Zhang, Xu Sun*, Houfeng Wang*.
    AAAI 2018
    [pdf][bibtex]

  17. Modeling Scientific Influence for Research Trending Topic Prediction.
    Chengyao Chen, Zhitao Wang, Wenjie Li, Xu Sun.
    AAAI 2018
    [pdf][bibtex]

  18. Query and Output: Generating Words by Querying Distributed Word Representations for Paraphrase Generation.
    Shuming Ma, Xu Sun*, Wei Li, Sujian Li, Wenjie Li, Xuancheng Ren.
    NAACL 2018
    [pdf] [code][bibtex] [ppt]


2017

  1. meProp: Sparsified Back Propagation for Accelerated Deep Learning with Reduced Overfitting.
    Xu Sun, Xuancheng Ren, Shuming Ma, Houfeng Wang.
    ICML 2017
    [pdf] [code][bibtex]

  2. Improving Semantic Relevance for Sequence-to-Sequence Learning of Chinese Social Media Text Summarization.
    Shuming Ma, Xu Sun*, Jingjing Xu, Houfeng Wang, Wenjie Li, Qi Su.
    ACL 2017
    [pdf][code] [bibtex][ppt]

  3. A Unified Model for Cross-Domain and Semi-Supervised Named Entity Recognition in Chinese Social Media.
    Hangfeng He, Xu Sun*.
    AAAI 2017: 3216-3222.
    [pdf][data][bibtex]

  4. F-Score Driven Max Margin Neural Network for Named Entity Recognition in Chinese Social Media.
    Hangfeng He, Xu Sun*.
    EACL 2017
    [pdf][data][bibtex]

  5. Addressing Domain Adaptation for Chinese Word Segmentation with Global Recurrent Structure.
    Shen Huang, Xu Sun, Houfeng Wang.
    IJCNLP 2017
    [pdf]

  6. Tag-Enhanced Tree-Structured Neural Networks for Implicit Discourse Relation Classification.
    Yizhong Wang, Sujian Li, Jingfeng Yang, Xu Sun, Houfeng Wang.
    IJCNLP 2017
    [pdf]

  7. Cascading Multiway Attentions for Document-level Sentiment Classification.
    Dehong Ma, Sujian Li, Xiaodong Zhang, Houfeng Wang, Xu Sun.
    IJCNLP 2017
    [pdf]

  8. Transfer Deep Learning for Low-Resource Chinese Word Segmentation with a Novel Neural Network.
    Jingjing Xu, Shuming Ma, Yi Zhang, Bingzhen Wei, Xiaoyan Cai, and Xu Sun*.
    NLPCC 2017
    [pdf]

  9. Lock-Free Parallel Perceptron for Graph-based Dependency Parsing.
    Xu Sun, Shuming Ma.
    arXiv 2017: 1703.00782.
    [pdf][bibtex]

  10. Transfer Learning for Low-Resource Chinese Word Segmentation with a Novel Neural Network.
    Jingjing Xu, Xu Sun*.
    arXiv 2017: 1702.04488.
    [pdf][bibtex]

  11. A Generic Online Parallel Learning Framework for Large Margin Models.
    Shuming Ma, Xu Sun*.
    arXiv 2017: 1703.00786.
    [pdf][bibtex]

  12. Label Embedding Network: Learning Label Representation for Soft Training of Deep Networks.
    Xu Sun, Bingzhen Wei, Xuancheng Ren, Shuming Ma.
    arXiv 2017: 1710.10393.
    [pdf]

  13. A Semantic Relevance Based Neural Network for Text Summarization and Text Simplification.
    Shuming Ma, Xu Sun*.
    arXiv 2017: 1710.02318.
    [pdf]

2016

  1. Asynchronous Parallel Learning for Neural Networks and Structured Models with Dense Features.
    Xu Sun.
    COLING 2016: 192-202
    [pdf][slide][slide_pdf][bibtex]

  2. Dependency-based Gated Recursive Neural Network for Chinese Word Segmentation.
    Jingjing Xu, Xu Sun*.
    ACL 2016: 567-572 (Short paper)
    [pdf][bibtex]

  3. Knowledge-Based Semantic Embedding for Machine Translation.
    C. Shi, S. Liu, S. Ren, S. Feng, M. Li, M. Zhou, Xu Sun, H. Wang.
    ACL 2016
    [pdf]

  4. Methods and Theories for Large-scale Structured Prediction
    Xu Sun, Yansong Feng.
    EMNLP 2016 Tutorial
    [download PPT] [download PDF]

  5. A New Recurrent Neural CRF for Learning Non-linear Edge Features.
    Shuming Ma, Xu Sun*.
    arXiv 2016: 1611.04233.
    [pdf][bibtex]

2015

  1. Multi-label Text Categorization with Joint Learning Predictions-as-Features Method.
    L. Li, B. Chang, S. Zhao, L. Sha, X. Sun, H. Wang.
    EMNLP 2015: 835-839
    [pdf]

  2. 书籍章节(特邀),《基于记忆的自然语言处理》,语言技术与计算语言学丛书(第11部)
    基于记忆的自然语言处理导读
    北京大学出版社,2015

  3. Towards Shockingly Easy Structured Classification: A Search-based Probabilistic Online Learning Framework.
    (Probabilistic Perceptron: A method with better accuracy than CRFs and almost as fast as perceptrons)
    Xu Sun.
    arXiv:1503.08381. 22 pages. 2015
    [pdf][bibtex]

2014

  1. Structure Regularization for Structured Prediction.
    Xu Sun.
    NIPS 2014:2402-2410
    [pdf][full version with proofs] [code & notes] [bibtex] [slide]

  2. Feature-Frequency-Adaptive Online Training for Fast and Accurate Natural Language Processing.
    Xu Sun, Wenjie Li, Houfeng Wang, Qin Lu.
    Computational Linguistics. 40(3): 563-586. MIT Press. 2014.
    [pdf][code] [bibtex]

  3. Coarse-grained Candidate Generation and Fine-grained Re-ranking for Chinese Abbreviation Prediction.
    L. Zhang, H. Wang, X. Sun.
    EMNLP2014: 1881-1890
    [pdf]

  4. Predicting Chinese Abbreviations with Minimum Semantic Unit and Global Constraints.
    L. Zhang, L. Li, H. Wang, X. Sun.
    EMNLP2014: 1405-1414
    [pdf]

2013

  1. Large-Scale Personalized Human Activity Recognition using Online Multi-Task Learning.
    Xu Sun, Hisashi Kashima, Naonori Ueda.
    IEEE Transactions on Knowledge and Data Engineering (TKDE). 25(11): 2551-2563. IEEE. 2013
    [pdf][code] [bibtex]

  2. Latent Structured Perceptrons for Large-Scale Learning with Hidden Information.
    Xu Sun, Takuya Matsuzaki, Wenjie Li.
    IEEE Transactions on Knowledge and Data Engineering (TKDE). 25(9): 2063-2075. IEEE. 2013
    [pdf][code] [bibtex]

  3. Learning Abbreviations from Chinese and English Terms by Modeling Non-local Information.
    X. Sun, N. Okazaki, J. Tsujii, H. Wang.
    ACM Transactions on Asian Language Information Processing (TALIP). Vol. 12, No. 2, Article 5, 17 pages. 2013
    [pdf][bibtex]

  4. Probabilistic Chinese Word Segmentation with Non-Local Information and Stochastic Training.
    X. Sun, Y. Zhang, T. Matsuzaki, Y. Tsuruoka, J. Tsujii.
    Information Processing & Management (IPM). 49. 626-636. Elsevier. 2013
    [pdf][bibtex]

  5. Generalized Abbreviation Prediction with Negative Full Forms and Its Application on Improving Chinese Web Search.
    X. Sun, W. Li, F. Meng, H. Wang.
    IJCNLP. 641-647. 2013
    [pdf][bibtex] [slide]

  6. A Unified Graph Model for Personalized Query-oriented Reference Paper Recommendation.
    F. Meng, D. Gao, W. Li, X. Sun, Y. Hou.
    CIKM. 1509-1512. 2013
    [pdf]

  7. Exploring Representations from Unlabeled Data with Co-training for Chinese Word Segmentation.
    L. Zhang, H. Wang, X. Sun, M. Mansur.
    EMNLP. 311-321. 2013
    [pdf]

2012

  1. Fast Online Training with Frequency-Adaptive Learning Rates for Chinese Word Segmentation and New Word Detection.
    Xu Sun, Houfeng Wang, Wenjie Li.
    ACL. 253–262. 2012
    [pdf][code] [bibtex] [slide]

  2. Fast Multi-task Learning for Query Spelling Correction.
    X. Sun, A. Shrivastava, P. Li.
    CIKM. 285-294. 2012
    [pdf][bibtex]

  3. Query Spelling Correction Using Multi-task Learning.
    X. Sun, A. Shrivastava, P. Li.
    International Conference on World Wide Web (WWW). Poster. 613-614. 2012
    [bibtex]

2011

  1. Online Multi-Task Learning for Personalized Activity Recognition.
    X. Sun, H. Kashima, R. Tomioka, N. Ueda, P. Li.
    International Conf. on Data Mining (ICDM). 1218-1223. 2011
    [pdf][bibtex]

  2. Large Scale Real-life Action Recognition Using Conditional Random Fields with Stochastic Training.
    X. Sun, H. Kashima, R. Tomioka, N. Ueda.
    PAKDD. 222-233. 2011
    [pdf][bibtex]

2010

  1. Averaged Stochastic Gradient Descent with Feedback: An Accurate, Robust, and Fast Training Method.
    X. Sun, H. Kashima, T. Matsuzaki and N. Ueda.
    International Conf. on Data Mining (ICDM). 1067-1072. 2010
    [pdf][bibtex]

  2. Learning Phrase-Based Spelling Error Models from Clickthrough Data.
    Xu Sun, Jianfeng Gao, Daniel Micol, Chris Quirk.
    ACL. 266-274. 2010
    [pdf][bibtex]

  3. A Large Scale Ranker-Based System for Search Query Spelling Correction.
    J. Gao, X. Li, D. Micol, C. Quirk, X. Sun.
    COLING. 358-366. 2010
    [pdf][bibtex]

2009

  1. Robust Approach to Abbreviating Terms: A Discriminative Latent Variable Model with Global Information.
    Xu Sun, Naoaki Okazaki, Junichi Tsujii.
    ACL. 905-913. 2009
    [pdf][bibtex]

  2. Latent Variable Perceptron Algorithm for Structured Classification.
    Xu Sun, Takuya Matsuzaki, Daisuke Okanohara, Junichi Tsujii.
    IJCAI. 1236-1242. 2009
    [pdf][code] [bibtex] [slide]

  3. A Discriminative Latent Variable Chinese Segmenter with Hybrid Word/Character Information.
    X. Sun, Y. Zhang, T. Matsuzaki, Y. Tsuruoka, J. Tsujii.
    NAACL. 56–64. 2009
    [pdf] [bibtex]

  4. Sequential Labeling with Latent Variables: An Exact Inference Algorithm and An Efficient Approximation.
    X. Sun, J. Tsujii.
    EACL. 772–780. 2009
    [pdf][bibtex]

2008

  1. Predicting Chinese Abbreviations from Definitions: An Empirical Learning Approach Using Support Vector Regression.
    X. Sun, H. Wang, B. Wang.
    Journal of Computer Sci. & Tech. (JCST) 23(4): 602-611. Springer. 2008.
    [pdf][bibtex]

  2. Modeling Latent-Dynamic in Shallow Parsing: A Latent Conditional Model with Improved Inference.
    X. Sun, L. Morency, D. Okanohara, J. Tsujii.
    COLING. 841-848. 2008
    [pdf] [bibtex]