Jiajun Zhang    张家俊 (In Chinese)
Ph.D.
Associate Professor
Natural Language Processing Group
National Laboratory of Pattern Recognition

Institute of Automation Chinese Academy of Sciences
Email: jjzhang@nlpr.ia.ac.cn or jiajunzhangwing@gmail.com

Education:
2002.9-2006.7  BS. College of Computer Science and Technology, Jilin University
2006.9-2011.7  Ph.D. Institute of Automation Chinese Academy of Sciences


Research Interests:
Natural Language Processing, Machine Translation, Multi-lingual Text Analysis, Deep Learning


News:

I will serve as Program Co-chair for CWMT-2018.

Our long paper "Towards Neural Machine Translation with Partially Aligned Corpora" has been accepted by IJCNLP-2017.

Two papers "Exploiting Word Internal Structures for Generic Chinese Sentence Representation" and "Multi-modal Summarization for Asynchronous Collection of Text, Image, Audio and Video" have been accepted by EMNLP-2017.

Our paper "Learning Sentence Representation with Guidance of Human Attention" has been accepted by IJCAI-2017.

Our paper "Neural System Combination for Machine Translation" has been accepted by ACL-2017. (The improvement is more than 5 BLEU score over single MT System including NMT.)



Recent Talks:

Neural Machine Translation and Some CASIA works. link. Nanjing University, 2016.10 (In Chinese)

Representation Learning for Natural Language Processing. link. Nanjing University of Science and Technology, 2016.10 (In Chinese)

Deep Learning for Statistical Machine Translation. link. Tutorial in CCL, 2016.10 (In Chinese)


Publications: (Google Scholar)

2017:

Yining Wang, Yang Zhao, Jiajun Zhang, Chengqing Zong and Zhengshan Xue. Towards Neural Machine Translation with Partially Aligned Corpora. To Appear in IJCNLP-2017.

Haoran Li, Junnan Zhu, Chong Ma, Jiajun Zhang and Chengqing Zong. Multi-modal Summarization for Asynchronous Collection of Text, Image, Audio and Video. In Proc. of EMNLP-2017. Welcome to use our data! Data (in English) Data (in Chinese)

Shaonan Wang, Jiajun Zhang and Chengqing Zong. Exploiting Word Internal Structures for Generic Chinese Sentence Representation. In Proc. of EMNLP-2017.

Shaonan Wang, Jiajun Zhang and Chengqing Zong. Learning Sentence Representation with Guidance of Human Attention. In Proc. of IJCAI-2017.

Long Zhou, Wenpeng Hu, Jiajun Zhang and Chengqing Zong. Neural System Combination for Machine Translation. In Proc. of ACL-2017.

Haoran Li, Jiajun Zhang and Chengqing Zong. Implicit Discourse Relation Recognition for English and Chinese with Multi-view Modeling and Effective Representation Learning. ACM Transactions on Asian and Low-Resource Language Information Processing 2017.

Huijia Wu, Jiajun Zhang and Chengqing Zong. A Dynamic Window Network for CCG Supertagging. In Proceedings of AAAI 2017.

2016:

EUREKA-MangoNMT: C++ CPU code for Attention-based Neural Machine Translation. link

Jiajun Zhang and Chengqing Zong. Exploiting Source-side Monolingual Data in Neural Machine Translation. In Proceedings of EMNLP-2016.

Jiajun Zhang, Yu Zhou and Chengqing Zong. Abstractive Cross-Language Summarization via Translation Model Enhanced Predicate Argument Structure Fusing. IEEE/ACM Transactions on Audio, Speech and Language Processing (IEEE/ACM TASLP), No. 10 Vol 24.

Huijia Wu, Jiajun Zhang and Chengqing Zong. An Empirical Exploration of Skip Connections for Sequential Tagging. In Proceedings of COLING 2016.

Wenpeng Hu, Jiajun Zhang and Nan Zheng. Different Contexts Lead to Different Word Embeddings. In Proceedings of COLING 2016.

Xiaomian Kang, Haoran Li, Long Zhou, Jiajun Zhang and Chengqing Zong. An End-to-End Chinese Discourse Parser with Adaptation to Explicit and Non-explicit Relation Recognition. In Proceedings of the Twentieth Conference on Computational Natural Language Learning: CoNLL Shared Task. 2016. First Place.

Xiaoqing Li, Jiajun Zhang and Chengqing Zong. Towards Zero Unknown Word in Neural Machine Translation. In Proceedings of IJCAI-2016.

Yang Liu, Jiajun Zhang, Chengqing Zong, Yating Yang and Xi Zhou. A Bilingual Discourse Corpus and Its Applications. In Proceedings of LREC-2016.

Guoping Huang, Jiajun Zhang, Yu Zhou and Chengqing Zong. A Simple, Straightforward and Effective Model for Joint Bilingual Terms Detection and Word Alignment in SMT. In Proceedings of NLPCC-2016.

Guoping Huang, Jiajun Zhang, Yu Zhou and Chengqing Zong. Learning from User Feedback for Machine Translation in Real-Time. In Proceedings of NLPCC-2016.

Haoran Li, Jiajun Zhang, Yu Zhou and Chengqing Zong. Predicting Implicit Discourse Relation with Multi-view Modeling and Effective Representation Learning. In Proceedings of NLPCC-2016.

Haoran Li, Jiajun Zhang, Yu Zhou and Chengqing Zong. GuideRank: A Guided Ranking Graph Model for Multilingual Multi-document Summarizationg. In Proceedings of NLPCC-2016.

Chuanhai Dong, Jiajun Zhang, Chengqing Zong, Masanori Hattori and Hui Di. Character-Based LSTM-CRF with Radical-Level Features for Chinese Named Entity Recognition. In Proceedings of NLPCC-2016.

Huijia Wu, Jiajun Zhang and Chengqing Zong. Neural-Based Combinatory Categorical Grammar Supertagging. Journal of Software, 2016. (In Chinese)

2015:
Jiajun Zhang and Chengqing Zong. Deep Neural Networks in Machine Translation: an Overview. IEEE Intelligent Systems, Sept./Oct. 2015, 30(5), pp. 16-25.

Jiajun Zhang, Shujie Liu, Mu Li, Ming Zhou and Chengqing Zong. Towards Machine Translation in Semantic Vector Space. ACM Transactions on Asian and Low-resource Language Information Processing, ACM TALLIP, No.2, Vol.14 (March 2015).

Jiajun Zhang, Dakun Zhang, and Jie Hao. Local Translation Prediction with Global Sentence Representation. In Proceedings of IJCAI-2015.

Jiajun Zhang, Shujie Liu, Mu Li, Ming Zhou and Chengqing Zong. Beyond Word-based Language Model in Statistical Machine Translation. arxiv.org/abs/1502.07920.

Guoping Huang, Jiajun Zhang, Yu Zhou, and Chengqing Zong. A New Input Method for Human Translators: Integrating Machine Translation Effectively and Imperceptibly. In Proceedings of IJCAI-2015.

Haoran Li, Jiajun Zhang and Chengqing Zong. Predicting Implicit Discourse Relations with Purely Distributed Representations. In Proceedings of CCL-2015.

Shujie Liu, Li Dong, Jiajun Zhang, Furu Wei, Mu Li, and Ming Zhou. Application of Deep Learning in Natural Language Processing (深度学习在自然语言处理中的应用). In CCCF-2015. (In Chinese)

2014:

Jiajun Zhang, Shujie Liu, Mu Li, Ming Zhou and Chengqing Zong. Bilingually-constrained Phrase Embeddings for Machine Translation. In Proc. of ACL 2014
.

Jiajun Zhang, Shujie Liu, Mu Li, Ming Zhou and Chengqing Zong. Mind the Gap: Machine Translation by Minimizing the Semantic Gap in Embedding Space. In Proc. of AAAI 2014
.

Feifei Zhai, Jiajun Zhang, Yu Zhou and Chengqing Zong. RNN-based Derivation Structure Prediction for SMT. In Proc. of ACL 2014 (short paper).

Yang Liu, Jiajun Zhang, Jie Hao and Dakun Zhang. Making Language Model as Small as Possible in Statistical Machine Translation. In Proc. of CWMT 2014 (Best Paper Award).


2013:
Jiajun Zhang, Feifei Zhai and Chengqing Zong. A Substitution-Translation-Restoration Framework for Handling Unknown Words in Statistical Machine Translation. Journal of Computer Science and Technology. 2013.

Jiajun Zhang and Chengqing Zong. A Unified Approach for Effectively Integrating Source-side Syntactic Reordering Rules into Phrase-based Translation
. International Journal of Language Resources and Evaluation. 2013.

Jiajun Zhang, Feifei Zhai and Chengqing Zong. Syntax-Based Translation with Bilingually Lexicalized Synchronous Tree Substitution Grammars. IEEE Transactions on Audio, Speech and Language Processing (TASLP), 2013.8.

Jiajun Zhang and Chengqing Zong. Learning a Phrase-based Translation Model from Monolingual Data with Application to Domain Adaptation. In Proc. of ACL 2013.

Feifei Zhai, Jiajun Zhang, Yu Zhou and Chengqing Zong. Handling Ambiguities of Bilingual Predicate-Argument Structures for SMT. In Proc. of ACL 2013.

Feifei Zhai, Jiajun Zhang, Yu Zhou and Chengqing Zong. Unsupervised Tree Induction for Tree-based Translation. Transactions of Association for Computational Linguistics (TACL), 2013.

Jiajun Zhang and Chengqing Zong. Progress and Trends of Machine Translation (机器翻译研究进展与趋势). In CCCF, 2013. (In Chinese)


2012:
Jiajun Zhang and Chengqing Zong. A Comparative Study on Discontinuous Phrase Translation In Proc. of NLPCC 2012.

Jiajun Zhang, Feifei Zhai and Chengqing Zong. Handling Unknown Words in Statistical Machine Translation from a New Perspective. In Proc. of NLPCC 2012. Best Paper Award

Feifei Zhai, Jiajun Zhang, Yu Zhou and Chengqing Zong. Machine Translation by Modeling Predicate Argument Structure Transformation. In Proc. of COLING-2012, Mumbai, India, 8-15 December 2012.

Feifei Zhai, Jiajun Zhang, Yu Zhou and Chengqing Zong. Tree-based Translation without Using Parse Trees. In Proc. of COLING-2012, Mumbai, India, 8-15 December 2012.


2011:
Jiajun Zhang, Feifei Zhai and Chengqing Zong. 2011.  Augmenting String-to-Tree Models with Fuzzy Use of Source-side SyntaxIn Proceedings of Conference on Empirical Methods in Natural Language Processing, EMNLP-2011, Edinburgh.

Feifei Zhai, Jiajun Zhang, Yu Zhou and Cheqing Zong (2011)  Simple but Effective Approaches to Improving Tree-to-Tree ModelIn Proceedings of MT Summit 2011.


2009:
Jiajun Zhang and Chengqing Zong (2009) A Framework for Effectively Integrating Hard and Soft Syntactic Rule into Phrase Based Translation. In Proceedings of Pacific Asia Conference on Language, Information and Computation, PACLIC 2009. Hong Kong. Best Paper Award

Maoxi Li, Jiajun Zhang, Yu Zhou and Chengqing Zong. (2009)  The CASIA Statistical Machine Translation System for IWSLT 2009. In Proceedings of International Workshop on Spoken Language Translation,  IWSLT 2009. Tokyo, Japan.


2008:
Jiajun Zhang, Chengqing Zong and Shoushan Li. 2008.Sentence Type based Reordering Model for Statistical Machine Translation.In Proceedings of International Conference on Computational Linguistics, COLING-2008 Manchester, UK.

Yanqing He, Jiajun Zhang, Maoxi Li, Licheng Fang, Yufeng Chen, Yu Zhou and Chengqing Zong. 2008.The CASIA Statistical Machine Translation Sytem for IWSLT2008.In Proceedings of International Workshop on Spoken Language Translation,  IWSLT 2008. Hawaii, US.


Awards:

PACLIC-2009, Best Paper;

NLPCC-2012, Best Paper;

CWMT-2014, Best Paper;

Qian Weichang Chinese Information Porcessing Science and Technology Award, 2014, First Prize

ACL-IJCNLP-2015, Outstanding Reviewer;

Young Elite Scientists Sponsorship Program by CAST (2015)

Youth Innovation Promotion Association Chinese Academy of Sciences (2017)




Research Activity :
PC Co-Chair: CWMT-2018.

Demo Co-Chair: NLPCC 2014; Area Co-Chair: NLPCC-2017.

Senior Program Committee: IJCAI (2017)

Program Committee: ACL (2014, 2015, 2017), EMNLP (2015, 2016), NAACL (2016), COLING (2014, 2016), IJCAI (2013, 2015, 2017), AAAI(2017,2018), NLPCC (2012-2017), PACLIC (2011-2017), IALP (2013-2017), CWMT (2009-2017).

Journal Reviewer: ACM Transactions on Asian Language Information Processing, IEEE/ACM Transactions on Audio Speech and Language Processing.