张玉洁

基本信息

教育背景

1979年9月-1983年7月 北京交通大学 计算机科学系

1983年9月-1986年6月 中国科学院计算技术研究所 硕士课程

1994年4月-1999年3月 日本电气通信大学 计算机科学系 博士课程

工作经历

中国科学院计算技术研究所

日本电气通信大学

日本ATR国际先端通信技术研究所

日本情报通信研究机构

招生研究方向

• 自然语言处理
• 机器翻译
• 多语言信息处理技术

研究方向

• 机器学习与认知计算
• 人工智能及应用
• 软件工程理论
• 计算机软件理论
• 计算机技术
• 软件工程
• 人工智能
• 网络与信息安全
• 大数据技术与工程

招生专业

• 计算机科学与技术硕士
• 软件工程硕士
• 计算机技术硕士
• 人工智能硕士
• 网络与信息安全硕士
• 大数据技术与工程硕士

科研项目

1. 国家自然科学基金“面上”：基于语义组合的开放域汉语复述研究，2019-01-01--2022-12-31，主持
   
2. 富士通中国研发中心：面向QA的问题句复述系统的构建，2018-01-20--2018-06-15，主持
   
3. 国家国际科技合作专项：面向科技文献的日汉双向实用型机器翻译合作研究子课题，2014年04月01日至2016年03月31日，主持
4. 国家自然科学基金“面上”：基于格依存树到串模型的日汉机器翻译研究，2014-01-01--2017-12-31，参加
5. 中国科学院自动化研究所：日汉语音机器翻译资源建设，2013-04-25--2013-12-15，主持
6. 富士通中国研发中心：汉日同族专利句对齐工具，2012-09-15--2013-03-31，主持
7. 中国科学院计算技术研究所：日语词法和句法分析工具合作开发合同，2012-06-01--2014-05-31，参加
8. 中国科学院中科院自动化所：收集日汉双语命名实体及开发日语命名实体识别与日汉命名实体翻译模块的合同书，2011-12-20--2013-06-30，参加
9. 人才基金：机器翻译研发平台的建设，2011-06-25--2013-08-31，主持

以往参加的科研项目

教学工作

论文/期刊

期刊论文

刘航, 刘明童, 张玉洁, 徐金安, 陈钰枫(2019). 采用 Stack-Tree LSTM 的汉语一体化依存分析模型[J]. 中文信息学报, 2019, 33(1): 10-17.

刘明童，张玉洁，徐金安, 陈钰枫(2018). 基于多特征融合编码的神经网络依存句法分析模型[J]. 中文信息学报, 2018, 32(12) : 18-25.

刘明童, 张玉洁, 徐金安, 陈钰枫(2018). 开放域上基于深度语义计算的复述模板获取方法[J]. 中文信息学报, 2018, 32(2) : 94-101.

Hang Liu,Mingtong Liu,Yujie Zhang ,Jinan Xu,Yufeng Chen(2018).Improved Character-Based Chinese Dependency Parsing by Using Stack-Tree LSTM[C]//CCF International Conference on Natural Language Processing and Chinese Computing. Springer, Cham, 2018: 203-212.

张苗苗, 刘明童, 张玉洁, 徐金安, 陈钰枫(2018). 融合Gate过滤机制与深度Bi-LSTM-CRF的汉语语义角色标注[J]. 情报工程, 2018, 4(2) : 045-053.

马军, 张玉洁, 徐金安, 陈钰枫(2017). 基于随机行走N步的汉语复述短语获取方法, 中国科学信息科学, 2017, 47(8):1066-1077.

Jun Ma, Yujie Zhang, Jinan Xu, Yufeng Chen（2016）. Chinese Paraphrases Acquisition Based on Random Walk N Step, Natural Language Understanding and Intelligent Applications. Springer International Publishing, 2016, 10102: 639-647.

Zhen Guo, Yujie Zhang*, Chen Su, Jinan Xu,  Hitoshi Isahara (2016)，Character-Level Dependency     Model for Joint Word Segmentation, POS Tagging, and Dependency Parsing in Chinese，IEICE         Transactions on Information and Systems，E99.D(1):257-264，January 2016.  

Te Luo, Yujie Zhang, Jinan Xu, Yufeng Chen（2016）. Iterative Integration of Unsupervised Features for Chinese Dependency Parsing, Springer International Publishing, 2016, 10102: 531-540.

许华婷，张玉洁，杨晓晖，单华，徐金安，陈钰枫（2015），基于Active Learning的中文分词领域自适应，中文信   息学报，Vol.29， No.5, pp.56-63.

苏晨,张玉洁,郭振,徐金安（2015）,使用源语言复述知识改善统计机器翻译性能[J],北京大学学报(自然科学版）     Vol. 51，Ｎo.２ pp.342-348.

JINAN XU; JIANGMING LIU; YUJIE ZHANG(2015),Word Similarity Computing Based on Hybrid Hierarchical   Structure by HowNet,Journal of Information Science & Engineering , Nov.2015, Vol. 31 Issue 6,   pp.2089-2101.

刘博佳，徐金安，陈钰枫，张玉洁（2015），基于字形与语音的音译单元对齐方法，北京大学学报(自然科学版)，     Vol.52， No.1, pp.75-80.

王东明，徐金安，陈钰枫，张玉洁（2015），基于单语语料的面向日语假名的日汉人名翻译对抽取方法，中文信息   学报，Vol.29， No.5, pp.84-90.

郭振,张玉洁,苏晨,徐金安（2014）,半监督的中文分词、词性标注和基于字符的依存句法分析联合模型,中文信息学报,2014,Vol.28,No.6,pp.1-8.

刘江鸣，徐金安，张玉洁 （2014），基于隐主题马尔科夫模型的多特征自动文摘，北京大学学报（自然科学版Vol.50,No.1，pp.187-193.

吴培昊,徐金安,谢军,张玉洁（2014）,融合格框架的基于语块的依存树到串日汉统计机器翻译模型,中文信息学报,2014,Vol.28,No.5,pp.133-140.

郭振,张玉洁,苏晨,徐金安（2013）,Exploration of N-gram Features for the Domain Adaptation of Chinese Word Segmentation[J],Natural Language Processing and Chinese Computing Communications in Computer and Information Science,2013-01,333（springer）,pp.121-131.

苏晨,张玉洁,郭振,徐金安（2013）,面向特定领域机器翻译的汉语分词方法[J],中文信息学报,2013,Vol.5,No.27,185-190.

殷乐, 张玉洁, 徐金安（2013）,基于虚拟上下文的统计机器翻译短语表的过滤[J],中文信息学报,2013,Vol.6,No.27,139-143

赵紫玉,徐金安,张玉洁,刘江鸣（2013）,规则与统计相结合的日语时间表达式识别[J] ,中文信息学报,2013,Vol.6,No.27,192-200

茹旷,徐金安,张玉洁,吴培昊（2013）,A Method to Construct Chinese-Japanese Named Entity Translation Equivalents Using Monolingual Corpora[J],Natural Language Processing and Chinese Computing,2013-11,400（springer）,164-175.

赵紫玉,徐金安,张玉洁,刘江鸣（2013）,日语时间表达式识别与日汉翻译研究[J],北京大学学报（自然科学版）,2013,Vol.1,1-7

岳金媛,徐金安,张玉洁（2013）,面向专利文献的汉语分词技术研究[J],北京大学学报(自然科学版),2013,Vol.01,159-164.

苏晨,张玉洁,郭振,徐金安（2013）,Exploring Multiple Chinese Word Segmentation Results Based on Linear Model[J],Natural Language Processing and Chinese Computing Communications in Computer and Information Science,2013-11,400（springer）,50-59.

刘江鸣,徐金安,张玉洁（2013）,基于隐主题马尔科夫模型的多特征自动文摘[J],北京大学学报,科学版,2013,Vol.1,1-7.

Wenliang Chen, Jun'ichi Kazama, Min Zhang, Yoshimasa Tsuruoka and Yujie Zhang, Yiou Wang, Kentaro Torisawa and Haizhou Li(2012),Bitext Dependency Parsing With Auto-Generated Bilingual Treebank,IEEE Transactions on Audio, Speech & Language Processing,Vol.20, Num.5, pp.1461-1472.

Wenliang Chen, Daisuke Kawahara, Kiyotaka Uchimoto,Yujie Zhang, Hitoshi Isahara(2009), Using Short Dependency Relations from Auto-Parsed Data for Chinese Dependency Parsing, ACM Transactions on Asian Language Information Processing, Vol. 8, Issue 3.

Yujie Zhang, Kou Kuroda, Emi Izumi (2007), Development of Language Resources for Natural Language Processing in Deep Level, Journal of National Institute of Information and Communications Technology, National Institute of Information and Communications Technology.

Yujie Zhang, Qing Ma, Qun Liu, Wenling Chen, Hitoshi Isahara (2006), Acquiring Translational Equivalence from a Japanese-Chinese Parallel Corpus, Computer Processing of Oriental Languages,Springer.

伊•达瓦,张玉洁,上园一知,大川茂树,章森,井佐原均,白井克彦 （2006），蒙古语语言-文字的自动处理, 中文信息学报Vol.20,No.4，56-62.

侯宏旭,刘群,张玉洁,井佐原均（2005）.2005年度863机器翻译评测方法研究与实施,中文信息学报,2006年Vol.20,No.B03,7-18.

张玉洁,山本和英 （2005）.中国語のコンピュータ処理について（中文信息处理综述）,漢字文献情報処理研究, 第６号, 102-109.

Yujie Zhang, Qing Ma and Hitoshi Isahara (2005), Construction of a Japanese-Chinese Bilingual Dictionary Using English as an Intermediary, International Journal of Computer Processing of Oriental Language, Vol.18, No.1, pp.23-39.

Yujie Zhang, Kazuhide Yamamoto (2005), Paraphrasing Spoken Chinese Using a Paraphrasing Corpus, Natural Language Engineering, Vol.11, No.4, pp.417-434.

Yujie Zhang, Qing Ma and Hitoshi Isahara(2005),Automatic Construction of a Japanese-Chinese Translation Dictionary Using English as an Intermediary, Journal of Natural Language Processing, Vol. 12, No. 2, pp. 63-85.(in Japanese).

Yujie Zhang, Qing Ma and Hitoshi Isahara (2005),Automatic Construction of a Japanese-Chinese Translation Dictionary Using English as an Intermediary,Journal of Natural Language Processing, Vol.12, No.2, pp.63-85.

Qing Ma, Kyoko Kanzaki, Yujie Zhang, Masaki Murata and Hitoshi Isahara (2004), Self-organizing semantic maps and its application to word alignment in　Japanese-Chinese parallel corpora, Neural Networks, Vol.17, No.8, pp.1241-1253.

张玉洁, 山本和英 (2003),汉语语句的自动改写, 中文信息学报, Vol. 17, No. 6, PP. 31-38.

Rei Oguro, Kazuhiko Ozeki, Yujie Zhang and Kazuyuki Takagi (2001), A Japanese sentence compaction algorithm based on phrase significance and inter-phrase dependency, Journal of Natural Language Processing,Vol.7, No.1, pp.13-30.(in Japanese).

Chengqing Zong, Yujie Zhang, Kazuhide Yamamoto, Masashi Sakamoto and Satoshi Shirai(2002), Chinese Utterance Paraphrasing for Spoken Language Translation, Journal of Chinese Language and Computing, Vol.12,No.1, pp.63-77.

Yujie Zhang and Kazuhiko Ozeki(2000), The application of decision trees to segmentation of long Japanese sentences, Journal of Natural Language Processing,Vol.7, No.1, pp.13-30.(in Japanese).

Yujie Zhang and Kazuhiko Ozeki (1998), The Application of Classification Trees to Bunsetsu Segmentation of Japanese Sentences, Journal of Natural Language Processing, Vol. 5, No. 4, pp. 17-33.

Yujie Zhang and Kazuhiko Ozeki(1997), Dependency Analysis of Japanese Sentences Using the Statistical Property of Dependency Distance between Phrases, Journal of Natural Language Processing, Vol.4, No.2, pp.3-19.(in Japanese).

张玉洁,周少柏 (1988), DBMS's 的报表生成系统,计算机研究与发展,Vol.25, No.9, pp.39-45。

会议论文(有审查)

 Jingsheng Cai, Masao Utiyama, Eiichiro Sumita and Yujie Zhang（2014）,Dependency-based Pre-ordering for Chinese-English Machine Translation, Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2),pp.155-160.

  苏晨,张玉洁,郭振,徐金安（2013）,面向特定领域机器翻译的汉语分词方法,第十二届全国计算语言学学术会议,中国苏州,185-185,2013-10.

郭振,张玉洁,苏晨,徐金安（2013）,Exploration of N-gram Features for the Domain Adaptation of Chinese Word Segmentation,NLP&CC2012,中国北京,121-121,2013-01.

苏晨,张玉洁,郭振,徐金安（2013）,Exploring Multiple Chinese Word Segmentation Results Based on Linear Model,NLP&CC2013,中国重庆,50-50,2013-11.

刘江鸣,徐金安,张玉洁（2013）,An Approach of Hybrid Hierarchical Structure for Computing Word Similarity by HowNet, IJCNLP,日本名古屋,927-927,2013-10.

赵紫玉,徐金安,张玉洁,刘江鸣（2013）,日语时间表达式识别与日汉翻译研究,NLP&CC2013,中国重庆,1-1,2013-11.

刘江鸣,徐金安,张玉洁（2013）,基于隐主题马尔科夫模型的多特征自动文摘,NLP&CC2013,中国重庆,1-1,2013-11.

赵紫玉,徐金安,张玉洁,刘江鸣（2013）,规则与统计相结合的日语时间表达式识别,CNCLL2013,中国苏州,1-1,2013-10.

吴培昊,徐金安,张玉洁（2013）,面向短语统计机器翻译的汉日联合分词研究,CNCLL2013,中国苏州,2-2,2013-10.

茹旷,徐金安,张玉洁,吴培昊（2013）,A Method to Construct Chinese-Japanese Named Entity Translation Equivalents Using Monolingual Corpora,NLP&CC2013,中国重庆,164-164,2013-11.

陈亮,徐金安,张玉洁（2012）,A Hybrid model for word alignment with bilingual corpus,CSAE2012,Zhangjiajie,99-99,2012-05.

蒋俊杰,徐金安,张玉洁（2012）,A Naïve Automatic MT Evaluation Method without Reference Translations,ISKE2011,shanghai,499-499,2012-01

Wenliang Chen, Jun’ichi Kazama, Min Zhang, Yoshimasa Tsuruoka, Yujie Zhang, Yiou Wang, Kentaro Torisawa, and Haizhou Li. (2011) ,SMT helps bitext dependency parsing, [EMNLP 2011]Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing, Edinburgh, Scotland, UK, July 27-31, 2011; pp.73-83.

Yiou Wang, Jun’ichi Kazama, Yoshimasa Tsuruoka,Wenliang Chen, Yujie Zhang and Kentaro Torisawa(2011), Improving Chinese Word Segmentation and POS Tagging with Semi-supervised Methods Using Large Auto-Analyzed Data, [IJCNLP 2011] Proceedings of the 5th International Joint Conference on Natural Language Processing, pp.309–317.

Yujie Zhang, Zhulong Wang, Kiyotaka Uchimoto and Qing Ma and Hitoshi Isahara (2008), Word Alignment Annotation in a Japanese-Chinese Parallel Corpus, 6th International Conference on Language Resources and Evaluation, Marrakech, Morocco.

Yujie Zhang, Qing Ma and Hitoshi Isahara (2007), Building Japanese-Chinese Translation Dictionary Based on EDR Japanese-English Bilingual Dictionary, 11^th Machine Translation Summit, Copenhagen, Denmark, pp.551-557.

Yujie Zhang, Qun Liu and Qing Ma, Chen Wenliang and Hitoshi Isahara (2006) ,Acquiring Translational Equivalence from a Japanese-Chinese Parallel Corpus, 21st International Conference on Computer Processing of Oriental Languages,Sentosa,Singapore, pp.378-386.

Chen Wenliang, Yujie Zhang and Isahara Hitoshi (2006), Chinese Chunking with Tri-training Learning, 21st International Conference on Computer Processing of Oriental Languages, Sentosa, Singapore, pp.466-473.

Chen Wenliang, Yujie Zhang and Isahara Hitoshi (2006), Chinese Named Entity Recognition with Conditional Random Fields, SIGHAN 2006 Bakeoff, Sydney, Australia, pp.118-121.

Chen Wenliang, Yujie Zhang and Isahara Hitoshi (2006), An Empirical Study of Chinese Chunking, Coling-ACL2006, Sydney, Australia, pp.97-104.

Yujie Zhang , Kiyotaka Uchimoto Qing Ma and Hitoshi Isahara (2005), Building an Annotated Japanese-Chinese Parallel Corpus – A Part of NICT Multi lingual Corpora, 10th Machine Translation Summit, Phuket, Thailand, pp.71-78.

Yujie Zhang, Qun Liu, Qing Ma and Hitoshi Isahara(2005), A Multi-aligner for Japanese-Chinese Parallel Corpora, 10th Machine Translation Summit, Phuket, Thailand, pp.133-140.

Yujie Zhang, Qing Ma and Hitoshi Isahara(2004), Use of Kanji Information in Constructing a　Japanese-Chinese Bilingual Lexicon, 4th Workshop on Asian Language Resources, Hainan, China, pp.39—46.

Kiyotaka Uchimoto, Yujie Zhang, Kiyoshi Sudo, Masaki Murata, Satoshi Sekine and Hitoshi Isahara(2004), Multilingual Aligned Parallel Treebank Corpus Reflecting Contextual Information and Its Applications,  MLR2004: PostCOLING Workshop on Multilingual Linguistic Resources, Geneva, Switzerland, pp.63-70.

Yujie Zhang, Qing Ma and Hitoshi Isahara(2003), Automatic Acquisition of A Japanese-Chinese Bilingual Lexicon Using English as an Intermediary, International Conference on Natural Language Processing and Knowledge Engineering, Beijing, China, pp.471-476.

Qing Ma, Kyoko Kanzaki, Yujie Zhang, Masaki Murata and Hitoshi Isahara(2003),Semantic Maps for Word Alignment in Bilingual Parallel Corpora, 2st SIGHAN Workshop on Chinese Language Processing, Sappora, Japan, pp.98-103.

Yujie Zhang and Kazuhide Yamamoto(2002), Paraphrasing of Chinese Utterances, 19th International Conference on Computational Linguistics, Taipei, Taiwan, pp.1163-1169.

Yujie Zhang, Kazuhide Yamamoto, Chengqing Zong and Masashi Sakamoto(2001),Paraphrasing Utterances by Reordering Words Using Semi-Automatically Acquired Patterns, 6th Natural Language Processing Pacific Rim Symposium, Tokyo, Japan, pp.195-202.

Chengqing Zong, Yujie Zhang, Kazuhide Yamamoto, Masashi Sakamoto and Satoshi Shirai(2001),Paraphrasing Chinese Utterances in Spoken Language Translation System, International Conference on Chinese Computing, Singapore, pp.395-401.

Chengqing Zong, Yujie Zhang, Kazuhide Yamamoto, Masashi Sakamoto and Satoshi Shirai, Approach to Spoken Chinese Paraphrasing Based on Feature Extraction, 6th  Natural Language Processing Pacific Rim Symposium, Tokyo, Japan, pp.551-556.

 Yujie Zhang and Kazuhide Yamamoto(2001), Analysis of Chinese Spoken Language for Automatic Paraphrasing, 19th International Conference on Computer Processing of Oriental Languages, Seoul, Korea, pp.290-293.

Kazuhide Yamamoto, Satoshi Shirai and Masashi Sakamoto and Yujie Zhang(2001), SANDGLASS: Twin Paraphrasing Spoken Language Translation, 19th International Conference on Computer Processing of Oriental Languages, Seoul, Korea, pp.154-159.

Yujie Zhang and Kazuhiko Ozeki(1999), Classification Tree Approach to Automatic Segmentation of Japanese Compound Sentences, 13th Pacific Asia Conference on Language, Information and Computation, Taipei, Taiwan, pp.241-250.

Kazuhiko Ozeki, Kazuyuki Kousaka and Yujie Zhang(1998),The Use of Prosodic Information in Syntactic Analysis of Japanese Utterances, International Workshop SPEECH and COMPUTER, pp.157-160.

Yujie Zhang and Kazuhiko Ozeki (1998), Automatic Bunsetsu Segmentation of Japanese Sentences Using a Classification Tree, 12th Pacific Asia Conference on Language, Information and Computation, Singapore, pp.230-235.

Kazuhiko Ozeki, Kazuyuki Kousaka and Yujie Zhang (1997), Syntactic Information Contained in Prosodic Features of Japanese Utterances, 5th European Conference on Speech Communication and Technology, Rhodes , Vol.3,  pp.1471-1474.

Kazuhiko Ozeki, Kazuyuki Kousaka and Yujie Zhang (1997), Effectiveness of Prosodic Information in Dependency Analysis of Japanese Sentences, 1st China-Japan Workshop on Spoken Language Processing, China, pp.123-128.

会议论文(无审查)

吴培昊,徐金安,殷乐,张玉洁（2013）,System Description of BJTU-NLP MT for NTCIR-10 PatentMT,NTCIR-10,日本东京,373-373,2013-06. 

吴培昊,徐金安,苏晨,张玉洁（2013）,北京交通大学CWMT2013评测技术报告,CWMT2013,昆明,1：1,2013-10.

蒋俊杰,徐金安,张玉洁（2012）,北京交通大学CWMT2011评测报告,CWMT2011,厦门,130-130,2012-01.

专著/译著

专利

1．机器翻译系统

    坂本 仁，山本 和英，张玉洁

    特許登録　特許番号：特許第3403715号

2.对齐系统与程序

    馬 青，张玉洁，村田 真樹，井佐原 均

    特許登録　特許番号：特許第3820452号

软件著作权

获奖与荣誉

社会兼职

中国中文信息学会理事，中国中文信息学会计算语言学专委会委员，中国人工智能学会自然语言理解专业委员会委员，中文信息处理学报编辑委员，IEICE Associate Editor，Coling、MT Summit、中国中文信息学会计算语言学大会、中国计算机学会自然语言处理大会、中国机器翻译年会、杂志Natural Language Processing、Algorithms等审稿人，日本早稻田大学博士生共同指导导师。