周明ACL候任主席 数据简化DataSimp 今天

数据简化DataSimp导读：介绍七个NLP方向和三个建议，希望大家出成果。附微软官网周明博士简历。(赞赏后下载本文PDF和周明invited talks9 PPT的ZIP包共10个文件)

如何在NLP领域做成一件事by周明ACL计算语言学会候任主席(附PDF公号发“NLP做事”下载本文35795字PDF和10讲座PPT)

目录

A  如何在NLP领域第一次做成一件事(3234字)

建议1：如何在NLP领域快速学会第一个技能？

建议2：如何选择第一个好题目？

建议3：如何写出第一篇论文？

B  微软周明博士简历(31673字)

1.中文作者简介

2.英文个人主页

参考文献(559字) Appx(1236字).数据简化DataSimp社区简介

---

A 如何在NLP领域第一次做成一件事(3234字)

如何在NLP领域第一次做成一件事

文|作者：周明，微软亚洲研究院2016-11-24，数据简化DataSimp©20190113Sun

自然语言处理(简称NLP)，是研究计算机处理人类语言的一门技术，包括：

1.句法语义分析：对于给定的句子，进行分词、词性标记、命名实体识别和链接、句法分析、语义角色识别和多义词消歧。

2.信息抽取：从给定文本中抽取重要的信息，比如，时间、地点、人物、事件、原因、结果、数字、日期、货币、专有名词等等。通俗说来，就是要了解谁在什么时候、什么原因、对谁、做了什么事、有什么结果。涉及到实体识别、时间抽取、因果关系抽取等关键技术。

3.文本挖掘(或者文本数据挖掘)：包括文本聚类、分类、信息抽取、摘要、情感分析以及对挖掘的信息和知识的可视化、交互式的表达界面。目前主流的技术都是基于统计机器学习的。

4.机器翻译：把输入的源语言文本通过自动翻译获得另外一种语言的文本。根据输入媒介不同，可以细分为文本翻译、语音翻译、手语翻译、图形翻译等。机器翻译从最早的基于规则的方法到二十年前的基于统计的方法，再到今天的基于神经网络(编码-解码)的方法，逐渐形成了一套比较严谨的方法体系。

5.信息检索：对大规模的文档进行索引。可简单对文档中的词汇，赋之以不同的权重来建立索引，也可利用1，2，3的技术来建立更加深层的索引。在查询的时候，对输入的查询表达式比如一个检索词或者一个句子进行分析，然后在索引里面查找匹配的候选文档，再根据一个排序机制把候选文档排序，最后输出排序得分最高的文档。

6.问答系统：对一个自然语言表达的问题，由问答系统给出一个精准的答案。需要对自然语言查询语句进行某种程度的语义分析，包括实体链接、关系识别，形成逻辑表达式，然后到知识库中查找可能的候选答案并通过一个排序机制找出最佳的答案。

7.对话系统：系统通过一系列的对话，跟用户进行聊天、回答、完成某一项任务。涉及到用户意图理解、通用聊天引擎、问答引擎、对话管理等技术。此外，为了体现上下文相关，要具备多轮对话能力。同时，为了体现个性化，要开发用户画像以及基于用户画像的个性化回复。

随着深度学习在图像识别、语音识别领域的大放异彩，人们对深度学习在NLP的价值也寄予厚望。再加上AlphaGo的成功，人工智能的研究和应用变得炙手可热。自然语言处理作为人工智能领域的认知智能，成为目前大家关注的焦点。很多研究生都在进入自然语言领域，寄望未来在人工智能方向大展身手。但是，大家常常遇到一些问题。俗话说，万事开头难。如果第一件事情成功了，学生就能建立信心，找到窍门，今后越做越好。否则，也可能就灰心丧气，甚至离开这个领域。这里针对给出我个人的建议，希望我的这些粗浅观点能够引起大家更深层次的讨论。

建议1：如何在NLP领域快速学会第一个技能？

我的建议是：找到一个开源项目，比如机器翻译或者深度学习的项目。理解开源项目的任务，编译通过该项目发布的示范程序，得到与项目示范程序一致的结果。然后再深入理解开源项目示范程序的算法。自己编程实现一下这个示范程序的算法。再按照项目提供的标准测试集测试自己实现的程序。如果输出的结果与项目中出现的结果不一致，就要仔细查验自己的程序，反复修改，直到结果与示范程序基本一致。如果还是不行，就大胆给项目的作者写信请教。在此基础上，再看看自己能否进一步完善算法或者实现，取得比示范程序更好的结果。

建议2：如何选择第一个好题目？

工程型研究生，选题很多都是老师给定的。需要采取比较实用的方法，扎扎实实地动手实现。可能不需要多少理论创新，但是需要较强的实现能力和综合创新能力。而学术型研究生需要取得一流的研究成果，因此选题需要有一定的创新。我这里给出如下的几点建议。

1.       先找到自己喜欢的研究领域。你找到一本最近的ACL会议论文集，从中找到一个你比较喜欢的领域。在选题的时候，多注意选择蓝海的领域。这是因为蓝海的领域，相对比较新，容易出成果。

2.       充分调研这个领域目前的发展状况。包括如下几个方面的调研：方法方面，是否有一套比较清晰的数学体系和机器学习体系；数据方面，有没有一个大家公认的标准训练集和测试集；研究团队，是否有著名团队和人士参加。如果以上几个方面的调研结论不是太清晰，作为初学者可能不要轻易进入。

3.       在确认进入一个领域之后，按照建议一所述，需要找到本领域的开源项目或者工具，仔细研究一遍现有的主要流派和方法，先入门。

4.       反复阅读本领域最新发表的文章，多阅读本领域牛人发表的文章。在深入了解已有工作的基础上，探讨还有没有一些地方可以推翻、改进、综合、迁移。注意做实验的时候，不要贪多，每次实验只需要验证一个想法。每次实验之后，必须要进行分析存在的错误，找出原因。

5.       对成功的实验，进一步探讨如何改进算法。注意实验数据必须是业界公认的数据。

6.       与已有的算法进行比较，体会能够得出比较一般性的结论。如果有，则去写一篇文章，否则，应该换一个新的选题。

建议3：如何写出第一篇论文？

接上一个问题，如果想法不错，且被实验所证明，就可开始写第一篇论文了。

1.     确定论文的题目。在定题目的时候，一般不要“…系统”、“…研究与实践”，要避免太长的题目，因为不好体现要点。题目要具体，有深度，突出算法。

2.       写论文摘要。要突出本文针对什么重要问题，提出了什么方法，跟已有工作相比，具有什么优势。实验结果表明，达到了什么水准，解决了什么问题。

3.       写引言。首先讲出本项工作的背景，这个问题的定义，它具有什么重要性。然后介绍对这个问题，现有的方法是什么，有什么优点。但是(注意但是)现有的方法仍然有很多缺陷或者挑战。比如(注意比如)，有什么问题。本文针对这个问题，受什么方法(谁的工作)之启发，提出了什么新的方法并做了如下几个方面的研究。然后对每个方面分门别类加以叙述，最后说明实验的结论。再说本文有几条贡献，一般写三条足矣。然后说说文章的章节组织，以及本文的重点。有的时候东西太多，篇幅有限，只能介绍最重要的部分，不需要面面俱到。

4.       相关工作。对相关工作做一个梳理，按照流派划分，对主要的最多三个流派做一个简单介绍。介绍其原理，然后说明其局限性。

5.       然后可设立两个章节介绍自己的工作。第一个章节是算法描述。包括问题定义，数学符号，算法描述。文章的主要公式基本都在这里。有时候要给出简明的推导过程。如果借鉴了别人的理论和算法，要给出清晰的引文信息。在此基础上，由于一般是基于机器学习或者深度学习的方法，要介绍你的模型训练方法和解码方法。第二章就是实验环节。一般要给出实验的目的，要检验什么，实验的方法，数据从哪里来，多大规模。最好数据是用公开评测数据，便于别人重复你的工作。然后对每个实验给出所需的技术参数，并报告实验结果。同时为了与已有工作比较，需要引用已有工作的结果，必要的时候需要重现重要的工作并报告结果。用实验数据说话，说明你比人家的方法要好。要对实验结果好好分析你的工作与别人的工作的不同及各自利弊，并说明其原因。对于目前尚不太好的地方，要分析问题之所在，并将其列为未来的工作。

6.       结论。对本文的贡献再一次总结。既要从理论、方法上加以总结和提炼，也要说明在实验上的贡献和结论。所做的结论，要让读者感到信服，同时指出未来的研究方向。

7.       参考文献。给出所有重要相关工作的论文。记住，漏掉了一篇重要的参考文献(或者牛人的工作)，基本上就没有被录取的希望了。

8.       写完第一稿，然后就是再改三遍。

9.       把文章交给同一个项目组的人士，请他们从算法新颖度、创新性和实验规模和结论方面，以挑剔的眼光，审核你的文章。自己针对薄弱环节，进一步改进，重点加强算法深度和工作创新性。

10.    然后请不同项目组的人士审阅。如果他们看不明白，说明文章的可读性不够。你需要修改篇章结构、进行文字润色，增加文章可读性。

11.    如投ACL等国际会议，最好再请英文专业或者母语人士提炼文字。

B微软周明博士简历(31673字)

微软周明博士简历

文|微软，数据简化DataSimp©20190113Sun

1.中文作者简介

周明，微软亚洲研究院首席研究员、ACL候任主席(president)、中国计算机学会中文信息技术专委会主任、中国中文信息学会常务理事、哈工大、天津大学、南开大学、山东大学等多所学校博士导师。1985年毕业于重庆大学，1991年获哈工大博士学位。1991-1993年清华大学博士后，随后留校任副教授。1996-1999访问日本高电社公司主持中日机器翻译研究。他是中国第一个中英翻译系统、日本最有名的中日机器翻译产品J-北京的发明人。1999年加入微软研究院并随后负责自然语言研究组，主持研制了微软输入法、对联、英库词典、中英翻译等著名系统。近年来与微软产品组合作开发了小冰(中国)、Rinna(日本)等聊天机器人系统。他发表了100余篇重要会议和期刊论文。拥有国际发明专利40余项。https://www.msra.cn/zh-cn/people/ming-zhou

Microsoft微软亚洲研究院

微软亚洲研究院副院长周明

1.1 个人简历

周明博士，微软亚洲研究院副院长、国际计算语言学协会(ACL)候任主席、中国计算机学会理事、中文信息技术专委会主任、术语工作委员会主任、中国中文信息学会常务理事、哈尔滨工业大学、天津大学、南开大学、山东大学等多所学校博士导师。

周明博士1985年毕业于重庆大学，1991年获哈尔滨工业大学博士学位。1991-1993年清华大学博士后，随后留校任副教授。1996-1999访问日本高电社公司领导中日机器翻译研究。他是中国第一个中英翻译系统CEMT-I(哈工大1989年)、日本最有名的中日机器翻译产品J-北京(日本高电社1998年)的研制者。

1999年，周明博士加入微软亚洲研究院，不久开始负责自然语言研究组。他带领团队进行了微软输入法、英库词典(必应词典)、中英翻译、微软中国文化系列(微软对联、微软字谜、微软绝句)等重要产品和项目的研发，并对微软Office、必应搜索、Windows等产品中的自然语言技术做出了重要贡献。近年来，周明博士领导研究团队与微软产品组合作开发了微软小冰(中国)、Rinna(日本)、Zo(美国)等聊天机器人系统。

周明博士发表了120余篇重要会议和期刊论文(包括50篇以上的ACL文章)，拥有国际发明专利40余项。他多年来通过微软与中国和亚太地区的高校合作计划，包括微软-高校联合实验室、微软实习生计划、微软-高校联合培养博士生计划、青年教师铸星培养计划，与高校和学术组织联合举办暑期学校和学术会议等多种形式，对推动自然语言处理在中国和亚太的卓越发展做出了杰出贡献。

1.2 相关文章

·        微软亚洲研究院NLP铁军“超越人类”技术揭秘【新智元】

·        微软亚洲研究院机器阅读系统在SQuAD挑战赛中率先超越人类水平

·        周明：中国NLP如何跻身世界顶尖水平？【AI科技评论】

·        从短句到长文，计算机如何学习阅读理解

·        周明：自然语言对话引擎

·        如何在NLP领域第一次做成一件事

·        统计机器学习——让计算机学会吟诗作赋

·        计算机能“理解”多少我们的语言了？

微软亚洲研究院首席研究员周明博士当选国际计算语言学协会(ACL)主席

英文个人主页https://www.microsoft.com/en-us/research/people/mingzhou/

2.英文个人主页

Ming Zhou, Assistant Managing Director

Contact Info Email  mingzhou@microsoft.com

Research areas Humanlanguage technologies

Groups NaturalLanguage Computing

2.1 About

Dr. Ming Zhou is an Assistant Managing Director ofMicrosoft Research Asia and research manager of the Natural Language ComputingGroup.  He is the president (electionmanifesto) of Association of Computational Linguistics (ACL). He is thechair of theChinese Computer Federation’s (CCF) ChineseInformation Technology Committee and an executive member of the Chinese Information Processing Society (CIPS).With his relentless efforts of decades, he made importantcontribution to the promotion and development of NLP, especially in China.

In 1989 he designed the CEMT-I machine translationsystem, the first experiment on Chinese-English machine translation obtainingthe government’s science and technology advancement prize in Mainland China. In1998, he designed the famous Chinese-Japanese machine translation softwareproduct J-Beijing in Japan which was later deployed in J-Server, a populartranslation service in Japan that won the Makoto Nagao Award given by theJapan Machine Translation Association in 2008. He is the leader of therenowned AI gaming of Chinese Couplets/Poetry Generation and Riddles (http://duilian.msra.cn), MS WindowsIME for Chinese and Japanese, and the English Assistance Search Engine, Engkoo,which won the WallStreet Journal’s 2010 Asian Innovation Readers’ Choice Award and waspackaged into Bing in 2011 as Bing Dictionary (http://cn.bing.com/dict/), and Engkoocloud IME which was packaged as Bing IME in 2012.In 2008, the system submitted by a joint team from MSR-NLPGroup, his Group and NRC and SRI obtained the top ranking in NISTChinese-English machine translation evaluation, and the system submittedfrom his group obtained the 2nd ranking in NIST English-Chinesemachine translation evaluation. In recent years, his group made importantbreakthrough in Machine Reading Comprehension (SQuAD) tasks, as the firstsystems reaching human-parity on both metrics of exact matching and fuzzymatching. The NMT system out of the joint effort of his group, Machine LearningGroup and MS Translator also reaches the human-parity on WMT 2018 evaluationtask. His group made important contributions to MS Bing search engine with NLPtechnologies such as word breaker, sentiment analysis, speller, dependencyparser, semantic parser and QnA. His group created Chinese-English, andCantonese-Chinese-English machine translation engine for MS Translator andSkype Translator. Recently, his group worked closely with Microsoftproduct teams to create well-known chat-bot products in China (Xiaoice), Japan(Rinna) and the US (Tay) with total of 200 million users. He has presented andpublished over 180 papers at top conferences (including 65+ ACL papers) and NLPjournals, and obtained 48 international patents. He received the Ability Awardfrom Microsoft CEO Satya Nadella in 2014 and  Beijing Outstanding WorkerMedal (May-1st Labor Medal) in 2018.

He has served as area chairs of ACL, EMNLP, COLING,IJCNLP, MT SUMMIT, AAAI, IJCAI during various periods in his career, and as PCchair or general chair of important conferences in Asian-Pacific such as AIRSand NLPCC. He was the associate editor of TALLIP, and an editorial board memberof Computational Linguistics and Machine Translation.

He has collaborated with universities across theAsia-Pacific and various academy associations to advance NLP research anddevelopment. For instance, in 2003 he worked with the Harbin Institute ofTechnology to set up an annual NLP summer school which has trained over 2000students since then. He is one of the main organizers of the NLPCC conferencesince 2011, which has become China’s flagship NLP conference. His group hashosted about 500 students for internships since 1999. As the director of theMicrosoft-Harbin Institute of Technology Joint Lab on NLP and theMicrosoft-Tsinghua Joint Lab on Networks and Media, and PhD advisors or adjunctprofessors at universities such as Harbin Institute of Technology, TianjinUniversity, Nankai University, Shandong University, Chongqing University,Dalian University of Technology, he contributed to increases in NLP research atthese universities.

Dr. Zhou received his B.S. in computer engineering fromChongqing University in 1985, and his M.S. degree and Ph.D. in computer sciencefrom Harbin Institute of Technology in 1988 and 1991. He did post-doctoral workat Tsinghua University from 1991 to 1993, later became an associate professorthere. From 1996-1999, during a sabbatical, he worked for Kodensha Ltd. Co. in Japan asthe leader of the Chinese-Japanese machine translation project. He joinedthe natural language group at Microsoft Research China (now Microsoft ResearchAsia) in September 1999 as researcher. He became the manager of this group in2001. His research interests include next generation search engines,statistical and neural machine translation, question-answering, chatbots,computer poetry, riddle resolving and generation, knowledge graph, commonsensegraph, semantic parser, text mining, user modelling and recommendation system.

New: I co-authored three books recently:

Machine Translation, High Education Publisher, 2018 (机器翻译，高教出版社，2018,简介)

Intelligence Question-Answering, High EducationPublisher, 2018 (智能问答，高教出版社，2018，简介)

Introduction to AI, Science Publisher, 2018  (人工智能导论，科学出版社，2018，简介)

2.2 Projects

Chatbots and Conversation As A Platform (CAAP)

Established: June 1, 2014

At Microsoft Build 2016 event, Microsoft CEO SatyaNadella said that chatbots, as next big thing, will have “as profoundan impact as previous shifts we’ve had.” The past paradigm shifts includegraphical user interface, the web browser and the touchscreen. ConversationsAs A platform(CAAP) has the promise of making booking a flight orbuying a new shirt as easy as sending a text message, with the potentialto make computing more accessible to users on mobile devices. Thisgroup has been worked on…

https://www.microsoft.com/en-us/research/project/chatbots-conversation-platform-caap/

2.3 SelectedPublications

New:I recently co-authored three books on NLP and AI:

1.   Machine Translation,High Education Publisher, 2018 （机器翻译，高教出版社，2018,简介）

2.   IntelligenceQuestion-Answering, High Education Publisher, 2018 （智能问答，高教出版社，2018，简介）

3.   Introduction to AI,Science Publisher, 2018 （人工智能导论，科学出版社，2018，简介

2018:

§ Zhao Yan, Nan Duan,Jun-Wei Bao, Peng Chen, Ming Zhou, Zhoujun Li, Response selection fromunstructured documents for human-computer conversation systems. Knowl.-BasedSyst. 142: 149-159 (2018)

§ Jun-Wei Bao, DuyuTang, Nan Duan, Zhao Yan, Yuanhua Lv, Ming Zhou, Tiejun Zhao, Table-to-Text:Describing Table Region With Natural Language. AAAI 2018: 5020-5027

§ Zhao Yan, Duyu Tang,Nan Duan, Shujie Liu, Wendi Wang, Daxin Jiang, Ming Zhou, Zhoujun Li,Assertion-Based QA With Question-Aware Open Information Extraction. AAAI 2018:6021-6028

§ Yikang Li, Nan Duan,Bolei Zhou, Xiao Chu, Wanli Ouyang, Xiaogang Wang, Ming Zhou, Visual QuestionGeneration as Dual Task of Visual Question Answering. CVPR 2018: 6116-6124

§ Xingxing Zhang,Mirella Lapata, Furu Wei, Ming Zhou, Neural Latent Extractive DocumentSummarization. EMNLP 2018: 779-784

§ Daya Guo, Yibo Sun,Duyu Tang, Nan Duan, Jian Yin, Hong Chi, James Cao, Peng Chen, Ming Zhou,Question Generation from SQL Queries Improves Neural Semantic Parsing. EMNLP2018: 1597-1607

§ Minghao Hu, YuxingPeng, Furu Wei, Zhen Huang, Dongsheng Li, Nan Yang, Ming Zhou, Attention-GuidedAnswer Distillation for Machine Reading Comprehension. EMNLP 2018: 2077-2086

§ Tao Ge, Qing Dou,Heng Ji, Lei Cui, Baobao Chang, Zhifang Sui, Furu Wei, Ming Zhou, Fine-grainedCoordinated Cross-lingual Text Stream Alignment for Endless Language KnowledgeAcquisition. EMNLP 2018: 2496-2506

§ Ming Zhou, What WillSearch Engines be Changed by NLP Advancements. PPT, ICTIR 2018:7

§ Chuanqi Tan, FuruWei, Wenhui Wang, Weifeng Lv, Ming Zhou, Multiway Attention Networks for ModelingSentence Pairs. IJCAI 2018: 4411-4417

§ Pan Lu, Lei Ji, WeiZhang, Nan Duan, Ming Zhou, Jianyong Wang, R-VQA: Learning Visual RelationFacts with Semantic Attention for Visual Question Answering. KDD 2018:1880-1889

§ Chuanqi Tan, FuruWei, Qingyu Zhou, Nan Yang, Weifeng Lv, Ming Zhou, I Know There Is No Answer:Modeling Answer Validation for Machine Reading Comprehension. NLPCC (1) 2018:85-97

§ Jian Yang, ShuangzhiWu, Dongdong Zhang, Zhoujun Li, Ming Zhou, Improved Neural Machine Translationwith Chinese Phonologic Features. NLPCC (1) 2018: 303-315

2017:

§ Zhao Yan, Nan Duan,Peng Chen, Ming Zhou, Jianshe Zhou, Zhoujun Li, Building Task-Oriented DialogueSystems for Online Shopping. AAAI 2017: 4618-4626

§ Shuangzhi Wu, MingZhou, Dongdong Zhang, Improved Neural Machine Translation with Source Syntax.IJCAI 2017: 4179-4185

§ Shuangzhi Wu,Dongdong Zhang, Shujie Liu, Ming Zhou, Modeling Indicative Context forStatistical Machine Translation. NLPCC 2017: 224-232

§ Jun-Wei Bao, NanDuan, Ming Zhou, Tiejun Zhao, An Information Retrieval-Based Approach toTable-Based Question Answering. NLPCC 2017: 601-611

2016:

·PengjieRen, Furu Wei, Zhumin Chen, Jun Ma and Ming Zhou，Redundancy-AwareSentence Regression Framework for Extractive Summarization, COLING 2016

·JunweiBao, Nan Duan, Zhao Yan, Ming Zhou and Tiejun Zhao,Constraint-Based QuestionAnswering with Knowledge Graph, COLING 2016

·ChaozhuoLi, Yu Wu, Wei Wu, Zhoujun Li and Ming Zhou, Detecting Context DependentMessages in a Conversational Environment, COLING 2016

·ShiFeng, Shujie Liu, Nan Yang, Mu Li, and Ming Zhou, Implicit Distortion andFertility Models for Attention-based Encoder-Decoder NMT Model, COLING 2016

·Tao Ge,Lei Cui, Baobao Chang, Zhifang Sui, and Ming Zhou, Event Detection with BurstyInformation Networks, COLING 2016

·Tao Ge,Lei Cui, Baobao Chang, Sujian Li, Ming Zhou and Zhifang Sui, Summarizing NewsStreams using Bursty Information Networks, EMNLP 2016

·ChuanqiTan, Furu Wei, Li Dong, Weifeng Lv and Ming Zhou, Solving and GeneratingChinese Character Riddles, EMNLP 2016.

·Zhao Yan,Nan Duan, Junwei Bao, Peng Chen, Ming Zhou and Zhoujun Li: DocChat:An Information Retrieval Approach for Chatbot Engines Using UnstructuredDocuments, ACL 2016

·Chen Shi,Shujie Liu, Shuo Ren, Mu Li, Ming Zhou, Xu Sun, Houfeng Wang: Knowledge-BasedSemantic Embedding for Machine Translation,ACL 2016

·Li Dong,Furu Wei, Ke Xu, Shixia Liu, Ming Zhou: AdaptiveMulti-Compositionality for Recursive Neural Network Models.IEEE/ACM Trans. Audio, Speech & Language Processing 24(3): 422-431 (2016)

·DuyuTang, Furu Wei, Bing Qin, Nan Yang, Ting Liu, Ming Zhou: SentimentEmbeddings with Applications to Sentiment Analysis.IEEE Trans. Knowl. Data Eng. 28(2): 496-509 (2016)

·Bei Chen,Jun Zhu, Nan Yang, Tian Tian, Ming Zhou, Bo Zhang: Jointly Modelinhttp://arxiv.org/pdf/1512.02009.pdfgTopics and Intents with Global Order Structure.AAAI 2016: 2711-2717

·ZiqiangCao, Chengyao Chen, Wenjie Li, Sujian Li, Furu Wei, Ming Zhou: TGSum: Build Tweet Guided Multi-DocumentSummarization Dataset. AAAI 2016: 2906-2912

·Yu Wu,Wei Wu, Zhoujun Li, Ming Zhou: ImprovingRecommendation of Tail Tags for Questions in Community Question Answering.AAAI 2016: 3066-3072

·KaiZhang, Wei Wu, Fang Wang, Ming Zhou, Zhoujun Li: LearningDistributed Representations of Data in Community Question Answering forQuestion Retrieval. WSDM 2016: 533-542

·Shi Feng,Shujie Liu, Mu Li, Ming Zhou: Implicit Distortion and Fertility Modelsfor Attention-based Encoder-Decoder NMT Model.CoRR abs/1601.03317 (2016)

2015:

·DehongGao, Furu Wei, Wenjie Li, Xiaohua Liu, Ming Zhou: Cross-lingualSentiment Lexicon Learning With Bilingual Word Graph Label Propagation.Computational Linguistics 41(1): 21-40 (2015)

·Li Dong,Furu Wei, Shujie Liu, Ming Zhou, Ke Xu: AStatistical Parsing Framework for Sentiment Classification.Computational Linguistics 41(2): 293-336 (2015)

·JiajunZhang, Shujie Liu, Mu Li, Ming Zhou, Chengqing Zong: TowardsMachine Translation in Semantic Vector Space.ACM Trans. Asian & Low-Resource Lang. Inf. Process. 14(2): 9 (2015)

·DuyuTang, Bing Qin, Furu Wei, Li Dong, Ting Liu, Ming Zhou: A JointSegmentation and Classification Framework for Sentence Level SentimentClassification. IEEE/ACM Trans. Audio, Speech &Language Processing 23(11): 1750-1761 (2015)

·Hyun-KyoOh, Sang-Wook Kim, Sunju Park, Ming Zhou: CanYou Trust Online Ratings? A Mutual Reinforcement Model for Trustworthy OnlineRating Systems. IEEE Trans. Systems, Man, and Cybernetics: Systems45(12): 1564-1576 (2015)

·Yu Wu,Wei Wu, Zhoujun Li, Ming Zhou: MiningQuery Subtopics from Questions in Community Question Answering.AAAI 2015: 339-345

·ZiqiangCao, Furu Wei, Li Dong, Sujian Li, Ming Zhou: Rankingwith Recursive Neural Networks and Its Application to Multi-Document Summarization.AAAI 2015: 2153-2159

·Li Dong,Furu Wei, Ming Zhou, Ke Xu: QuestionAnswering over Freebase with Multi-Column Convolutional Neural Networks.ACL (1) 2015: 260-269

·Yang Liu,Furu Wei, Sujian Li, Heng Ji, Ming Zhou, Houfeng Wang: A Dependency-Based Neural Network forRelation Classification. ACL (2) 2015: 285-290

·ShuangzhiWu, Dongdong Zhang, Ming Zhou, Tiejun Zhao: EfficientDisfluency Detection with Transition-based Parsing.ACL (1) 2015: 495-503

·ZiqiangCao, Furu Wei, Sujian Li, Wenjie Li, Ming Zhou, Houfeng Wang: LearningSummary Prior Representation for Extractive Summarization.ACL (2) 2015: 829—833

·PengchengYin, Nan Duan, Ben Kao, Jun-Wei Bao, Ming Zhou: Answering Questions with Complex SemanticConstraints on Open Knowledge Bases.CIKM 2015: 1301-1310

·ZhouZhao, Furu Wei, Ming Zhou, Wilfred Ng: Cold-StartExpert Finding in Community Question Answering via Graph Regularization.DASFAA (1) 2015: 21-38

·ZhouZhao, Furu Wei, Ming Zhou, Weikeng Chen, Wilfred Ng: Crowd-SelectionQuery Processing in Crowdsourcing Databases: A Task-Driven Approach.EDBT 2015: 397-408

·Rui Lin,Shujie Liu, Muyun Yang, Mu Li, Ming Zhou, Sheng Li: HierarchicalRecurrent Neural Network for Document Modeling.EMNLP 2015: 899-907

·Li Dong,Furu Wei, Hong Sun, Ming Zhou, Ke Xu: AHybrid Neural Model for Type Classification of Entity Mentions.IJCAI 2015: 1243-1249

·QinglinLi, Shujie Liu, Rui Lin, Mu Li, Ming Zhou: EntityTranslation with Collective Inference in Knowledge Graph.NLPCC 2015: 49-63

·JiajunZhang, Shujie Liu, Mu Li, Ming Zhou, Chengqing Zong: Beyond Word-based Language Model inStatistical Machine Translation. CoRRabs/1502.01446 (2015

·XiaojunWan, Ziqiang Cao, Furu Wei, Sujian Li, Ming Zhou: Multi-DocumentSummarization via Discriminative Summary Reranking.CoRR abs/1507.02062 (2015)

·Yang Liu,Furu Wei, Sujian Li, Heng Ji, Ming Zhou, Houfeng Wang: A Dependency-Based Neural Network forRelation Classification. CoRR abs/1507.04646 (2015)

·ZiqiangCao, Chengyao Chen, Wenjie Li, Sujian Li, Furu Wei, Ming Zhou: TGSum: Build Tweet Guided Multi-DocumentSummarization Dataset. CoRR abs/1511.08417 (2015)

·Bei Chen,Jun Zhu, Nan Yang, Tian Tian, Ming Zhou, Bo Zhang: Jointly Modeling Topics and Intents withGlobal Order Structure. CoRR abs/1512.02009 (2015)

2014:

·Bo Wang,Ming Zhou, Shujie Liu, Mu Li, Dongdong Zhang: Woodpecker:An Automatic Methodology for Machine Translation Diagnosis with Rich LinguisticKnowledge. J. Inf. Sci. Eng. 30(5): 1407-1424 (2014)

·Lei Cui,Ming Zhou, Qiming Chen, Dongdong Zhang, Mu Li: MachineTranslation with Real-Time Web Search.AAAI 2014: 23-29

·Li Dong,Furu Wei, Ming Zhou, Ke Xu: AdaptiveMulti-Compositionality for Recursive Neural Models with Applications toSentiment Analysis. AAAI 2014: 1537-1543

·JiajunZhang, Shujie Liu, Mu Li, Ming Zhou, Chengqing Zong: Mindthe Gap: Machine Translation by Minimizing the Semantic Gap in Embedding Space.AAAI 2014: 1657-1664

·Li Dong,Furu Wei, Chuanqi Tan, Duyu Tang, Ming Zhou, Ke Xu: AdaptiveRecursive Neural Network for Target-dependent Twitter Sentiment Classification.ACL (2) 2014: 49-54

·JiajunZhang, Shujie Liu, Mu Li, Ming Zhou, Chengqing Zong: Bilingually-constrainedPhrase Embeddings for Machine Translation.ACL (1) 2014: 111-121

·Lei Cui,Dongdong Zhang, Shujie Liu, Qiming Chen, Mu Li, Ming Zhou, Muyun Yang: LearningTopic Representation for SMT with Neural Networks.ACL (1) 2014: 133-143

·Jun-WeiBao, Nan Duan, Ming Zhou, Tiejun Zhao: Knowledge-BasedQuestion Answering as Machine Translation.ACL (1) 2014: 967-976

·ShujieLiu, Nan Yang, Mu Li, Ming Zhou: ARecursive Recurrent Neural Network for Statistical Machine Translation.ACL (1) 2014: 1491-1500

·DuyuTang, Furu Wei, Nan Yang, Ming Zhou, Ting Liu, Bing Qin:LearningSentiment-Specific Word Embedding for Twitter Sentiment Classification.ACL (1) 2014: 1555-1565

·KaiZhang, Wei Wu, Haocheng Wu, Zhoujun Li, Ming Zhou: QuestionRetrieval with High Quality Answers in Community Question Answering.CIKM 2014: 371-380

·ZhouZhao, James Cheng, Furu Wei, Ming Zhou, Wilfred Ng, Yingjun Wu: SocialTransfer:Transferring Social Knowledge for Cold-Start Cowdsourcing.CIKM 2014: 779-788

·DuyuTang, Furu Wei, Bing Qin, Ming Zhou, Ting Liu: BuildingLarge-Scale Twitter-Specific Sentiment Lexicon : A Representation LearningApproach. COLING 2014: 172-182

·HailongCao, Dongdong Zhang, Mu Li, Ming Zhou, Tiejun Zhao: ALexicalized Reordering Model for Hierarchical Phrase-based Translation.COLING 2014: 1144-1153

·HailongCao, Dongdong Zhang, Ming Zhou, Tiejun Zhao: SoftDependency Matching for Hierarchical Phrase-based Machine Translation.COLING 2014: 2227-2236

·DuyuTang, Furu Wei, Bing Qin, Li Dong, Ting Liu, Ming Zhou: AJoint Segmentation and Classification Framework for Sentiment Analysis.EMNLP 2014: 477-487

·Min-ChulYang, Nan Duan, Ming Zhou, Hae-Chang Rim: JointRelational Embeddings for Knowledge-based Question Answering.EMNLP 2014: 645-650

·Hong Sun,Furu Wei, Ming Zhou: AnswerExtraction with Multiple Extraction Engines for Web-Based Question Answering.NLPCC 2014: 321-332

·HaochengWu, Wei Wu, Ming Zhou, Enhong Chen, Lei Duan, Heung-Yeung Shum: Improvingsearch relevance for short queries in community question answering.WSDM 2014: 43-52

·Li Dong,Furu Wei, Shujie Liu, Ming Zhou, Ke Xu: AStatistical Parsing Framework for Sentiment Classification.CoRR abs/1401.6330 (2014)

2013:

·Lei Cui,Dongdong Zhang, Shujie Liu, Mu Li, and Ming Zhou, CollectiveCorpus Weighting and Phrase Scoring for SMT using Graph-based Random Walk,NLP-CC, November 2013

·XiaohuaLiu, Ming Zhou: Two-stageNER for tweets with clustering. Inf.Process. Manage. 49(1): 264-273 (2013)

·XiaohuaLiu, Furu Wei, Shaodian Zhang, Ming Zhou: Namedentity recognition for tweets. ACMTIST 4(1): 3 (2013)

·JinhanKim, Seung-won Hwang, Long Jiang, Young-In Song, Ming Zhou: EntityTranslation Mining from Comparable Corpora: Combining Graph Mapping with CorpusLatent Features. IEEE Trans. Knowl. Data Eng. 25(8):1787-1800 (2013)

·Li Dong,Furu Wei, Yajuan Duan, Xiaohua Liu, Ming Zhou, Ke Xu: TheAutomated Acquisition of Suggestions from Tweets.AAAI 2013

·DehongGao, Furu Wei, Wenjie Li, Xiaohua Liu, Ming Zhou: Co-TrainingBased Bilingual Sentiment Lexicon Learning.AAAI (Late-Breaking Developments) 2013

·ZhengyanHe, Shujie Liu, Mu Li, Ming Zhou, Longkai Zhang, Houfeng Wang: LearningEntity Representation for Entity Disambiguation.ACL (2) 2013: 30-34

·ChenguangWang, Nan Duan, Ming Zhou, Ming Zhang: ParaphrasingAdaptation for Web Search Ranking. ACL (2)2013: 41-46

·Nan Yang,Shujie Liu, Mu Li, Ming Zhou, Nenghai Yu: WordAlignment Modeling with Context Dependent Deep Neural Network.ACL (1) 2013: 166-175

·Lei Cui,Dongdong Zhang, Shujie Liu, Mu Li, Ming Zhou: BilingualData Cleaning for SMT using Graph-based Random Walk.ACL (2) 2013: 340-345

·XiaohuaLiu, Yitong Li, Haocheng Wu, Ming Zhou, Furu Wei, Yi Lu: EntityLinking for Tweets. ACL (1) 2013: 1304-1311

·YukiArase, Ming Zhou: MachineTranslation Detection from Monolingual Web-Text.ACL (1) 2013: 1597-1607

·XiujuanChai, Guang Li, Xilin Chen, Ming Zhou, Guobin Wu, Hanjing Li: VisualComm:a tool to support communication between deaf and hearing persons with theKinect. ASSETS 2013: 76

·Hyun-KyoOh, Sang-Wook Kim, Sunju Park, Ming Zhou: Trustableaggregation of online ratings. CIKM2013: 1233-1236

·ZhengyanHe, Shujie Liu, Yang Song, Mu Li, Ming Zhou, Houfeng Wang: Efficient Collective Entity Linking withStacking. EMNLP 2013: 426-435

·Lei Cui,Xilun Chen, Dongdong Zhang, Shujie Liu, Mu Li, Ming Zhou: Multi-DomainAdaptation for SMT Using Multi-Task Learning.EMNLP 2013: 1055-1065

·Hong Sun,Nan Duan, Yajuan Duan, Ming Zhou: AnswerExtraction from Passage Graph for Question Answering.IJCAI 2013

2012:

·Jing He,Ming Zhou, Long Jiang: GeneratingChinese Classical Poems with Statistical Machine Translation Models.AAAI 2012

·XiaohuaLiu, Zhongyang Fu, Furu Wei, Ming Zhou: CollectiveNominal Semantic Role Labeling for Tweets.AAAI 2012

·XiaohuaLiu, Xiangyang Zhou, Zhongyang Fu, Furu Wei, Ming Zhou: ExactingSocial Events for Tweets Using a Factor Graph.AAAI 2012

·XiaohuaLiu, Furu Wei, Ming Zhou: QuickView:NLP-based Tweet Search. ACL (System Demonstrations) 2012: 13-18

·Hong Sun,Ming Zhou: JointLearning of a Dual SMT System for Paraphrase Generation.ACL (2) 2012: 38-42

·    Seung-WookLee, Dongdong Zhang, Mu Li, Ming Zhou, Hae-Chang Rim: TranslationModel Size Reduction for Hierarchical Phrase-based Statistical MachineTranslation. ACL (2) 2012: 291-295

·ShujieLiu, Chi-Ho Li, Mu Li, Ming Zhou: LearningTranslation Consensus with Structured Label Propagation.ACL (1) 2012: 302-310

·XiaohuaLiu, Ming Zhou, Xiangyang Zhou, Zhongyang Fu, Furu Wei: JointInference of Named Entity Recognition and Normalization for Tweets.ACL (1) 2012: 526-535

·XinfanMeng, Furu Wei, Xiaohua Liu, Ming Zhou, Ge Xu, Houfeng Wang: Cross-Lingual Mixture Model for SentimentClassification. ACL (1) 2012: 572-581

·YajuanDuan, Furu Wei, Ming Zhou, Heung-Yeung Shum: Graph-basedcollective classification for tweets.CIKM 2012: 2323-2326

·YajuanDuan, Zhimin Chen, Furu Wei, Ming Zhou, Heung-Yeung Shum: TwitterTopic Summarization by Ranking Tweets using Social Influence and ContentQuality. COLING 2012: 763-780

·XinfanMeng, Furu Wei, Ge Xu, Longkai Zhang, Xiaohua Liu, Ming Zhou, Houfeng Wang: Lost inTranslations? Building Sentiment Lexicons using Context Based MachineTranslation. COLING (Posters) 2012: 829-838

·XiaohuaLiu, Yitong Li, Furu Wei, Ming Zhou: Graph-BasedMulti-Tweet Summarization using Social Signals.COLING 2012: 1699-1714

·Nan Duan,Mu Li, Ming Zhou: ForcedDerivation Tree based Model Training to Statistical Machine Translation.EMNLP-CoNLL 2012: 445-454

·ShujieLiu, Chi-Ho Li, Mu Li, Ming Zhou: Re-trainingMonolingual Parser Bilingually for Syntactic SMT.EMNLP-CoNLL 2012: 854-862

·XinfanMeng, Furu Wei, Xiaohua Liu, Ming Zhou, Sujian Li, Houfeng Wang: Entity-centrictopic-oriented opinion summarization in twitter.KDD 2012: 379-387

2011:

·MatthewR. Scott, Xiaohua Liu, Ming Zhou. Towardsa Specialized Search Engine for Language Learners.Proceedings of the IEEE, Vol.99, No.9, pp.1462-1465, Sept. 2011

·Lei Cui,Dongdong Zhang, Mu Li and Ming Zhou. FunctionWord Generation in Statistical Machine Translation Systems.Machine Translation Summit XIII, September 2011

·XiaohuaLiu, Kuan Li, Ming Zhou, Zhongyang Xiong: EnhancingSemantic Role Labeling for Tweets Using Self-Training.AAAI 2011

·MatthewR. Scott, Xiaohua Liu, Ming Zhou: Engkoo:Mining the Web for Language Learning.ACL (System Demonstrations) 2011: 44-49

·LongJiang, Mo Yu, Ming Zhou, Xiaohua Liu, Tiejun Zhao: Target-dependentTwitter Sentiment Classification. ACL2011: 151-160

·XiaohuaLiu, Shaodian Zhang, Furu Wei, Ming Zhou: RecognizingNamed Entities in Tweets. ACL 2011: 359-367

·Nan Duan,Mu Li, Ming Zhou: HypothesisMixture Decoding for Statistical Machine Translation.ACL 2011: 1258-1267

·XiaohuaLiu, Bo Han, Ming Zhou: CorrectingVerb Selection Errors for ESL with the Perceptron.CICLing (2) 2011: 411-423

·XiaolongWang, Furu Wei, Xiaohua Liu, Ming Zhou, Ming Zhang: Topicsentiment analysis in twitter: a graph-based hashtag sentiment classificationapproach. CIKM 2011: 1031-1040

·JinhanKim, Long Jiang, Seung-won Hwang, Young-In Song, Ming Zhou: Miningentity translations from comparable corpora: a holistic graph mapping approach.CIKM 2011: 1295-1304

·XiaohuaLiu, Kuan Li, Ming Zhou, Zhongyang Xiong: CollectiveSemantic Role Labeling for Tweets with Clustering.IJCAI 2011: 1832-1837

·ChenhaoTan, Lillian Lee, Jie Tang, Long Jiang, Ming Zhou, Ping Li: User-level sentiment analysis incorporatingsocial networks. KDD 2011: 1397-1405

·XiaohuaLiu, Long Jiang, Furu Wei, Ming Zhou: QuickView:advanced search of tweets. SIGIR 2011: 1275-1276

·Duo Ding,Xingping Jiang, Matthew R. Scott, Ming Zhou, Yong Yu: Tulsa:web search for writing assistance. SIGIR2011: 1287-1288

·ChenhaoTan, Lillian Lee, Jie Tang, Long Jiang, Ming Zhou, Ping Li: User-level sentiment analysis incorporatingsocial networks. CoRR abs/1109.6018 (2011)

2010:

·XiaohuaLiu, Ming Zhou: Evaluatingthe Quality of Web-Mined Bilingual Sentence Pairs.Int. J. of Asian Lang. Proc. 20(4): 171-179 (2010)

·Wei Gao,Cheng Niu, Jian-Yun Nie, Ming Zhou, Kam-Fai Wong, Hsiao-Wuen Hon: Exploitingquery logs for cross-lingual query suggestions.ACM Trans. Inf. Syst. 28(2) (2010)

·Lei Cui,Dongdong Zhang, Mu Li, Ming Zhou, Tiejun Zhao: A JointRule Selection Model for Hierarchical Phrase-Based Translation.ACL (Short Papers) 2010: 6-11

·ShujieLiu, Chi-Ho Li, Ming Zhou: DiscriminativePruning for Discriminative ITG Alignment.ACL 2010: 316-324

·Lei Cui,Dongdong Zhang, Mu Li, Ming Zhou, Tiejun Zhao: HybridDecoding: Decoding with Partial Hypotheses Combination over Multiple SMTSystems. COLING (Posters) 2010: 214-222

·YajuanDuan, Long Jiang, Tao Qin, Ming Zhou, Heung-Yeung Shum: AnEmpirical Study on Learning to Rank of Tweets.COLING 2010: 295-303

·Nan Duan,Hong Sun, Ming Zhou: TranslationModel Generalization using Probability Averaging for Machine Translation.COLING 2010: 304-312

·Nan Duan,Mu Li, Dongdong Zhang, Ming Zhou: MixtureModel-based Minimum Bayes Risk Decoding using Multiple Machine TranslationSystems. COLING 2010: 313-321

·Gum-WonHong, Chi-Ho Li, Ming Zhou, Hae-Chang Rim: AnEmpirical Study on Web Mining of Parallel Data.COLING 2010: 474-482

·Mu Li,Yinggong Zhao, Dongdong Zhang, Ming Zhou: AdaptiveDevelopment Data Selection for Log-linear Model in Statistical MachineTranslation. COLING 2010: 662-670

·XiaohuaLiu, Kuan Li, Bo Han, Ming Zhou, Long Jiang, Zhongyang Xiong, Changning Huang: SemanticRole Labeling for News Tweets. COLING2010: 698-706

·XiaohuaLiu, Kuan Li, Bo Han, Ming Zhou, Long Jiang, Daniel Tse, Zhongyang Xiong: CollectiveSemantic Role Labeling on Open News Corpus by Leveraging Redundancy.COLING (Posters) 2010: 725-729

·ShujieLiu, Chi-Ho Li, Ming Zhou: ImprovedDiscriminative ITG Alignment using Hierarchical Phrase Pairs andSemi-supervised Training. COLING (Posters) 2010: 730-738

·XiaohuaLiu, Bo Han, Kuan Li, Stephan Hyeonjun Stiller, Ming Zhou: SRL-BasedVerb Selection for ESL. EMNLP 2010: 1068-1076

·XiaohuaLiu, Ming Zhou:Evaluating the Quality of Web-Mined Bilingual Sentences Using MultipleLinguistic Features. IALP 2010: 281-284

2009:

·Mu Li,Nan Duan, Dongdong Zhang, Chi-Ho Li, Ming Zhou: CollaborativeDecoding: Partial Hypothesis Re-ranking Using Translation Consensus betweenDecoders. ACL/IJCNLP 2009: 585-592

·LongJiang, Shiquan Yang, Ming Zhou, Xiaohua Liu, Qingsheng Zhu: MiningBilingual Data from the Web with Adaptively Learnt Patterns.ACL/IJCNLP 2009: 870-878

·Wei Gao,John Blitzer, Ming Zhou, Kam-Fai Wong: ExploitingBilingual Information to Improve Web Search.ACL/IJCNLP 2009: 1075-1083

·Wei Gao,Cheng Niu, Ming Zhou, Kam-Fai Wong: JointRanking for Multilingual Web Search.ECIR 2009: 114-125 (best paper)

·TongXiao, Mu Li, Dongdong Zhang, Jingbo Zhu, Ming Zhou: BetterSynchronous Binarization for Machine Translation.EMNLP 2009: 362-370

·Nan Duan,Mu Li, Tong Xiao, Ming Zhou: TheFeature Subspace Method for SMT System Combination.EMNLP 2009: 1096-1104

·MingZhou, Long Jiang, Jing He: GeneratingChinese Couplets and Quatrain Using a Statistical Approach.PACLIC 2009: 43-52

2008:

·DongdongZhang, Mu Li, Nan Duan, Chi-Ho Li, Ming Zhou: MeasureWord Generation for English-Chinese SMT Systems.ACL 2008: 89-96

·ShiqiZhao, Cheng Niu, Ming Zhou, Ting Liu, Sheng Li: CombiningMultiple Resources to Improve SMT-based Paraphrasing Model.ACL 2008: 1021-1029

·Wei Gao,John Blitzer, Ming Zhou: UsingEnglish information in non-English web search.CIKM-iNEWS 2008: 17-24

·LongJiang, Ming Zhou: GeneratingChinese Couplets using a Statistical MT Approach.COLING 2008: 377-384

·MingZhou, Bo Wang, Shujie Liu, Mu Li, Dongdong Zhang, Tiejun Zhao: DiagnosticEvaluation of Machine Translation Systems Using Automatically ConstructedLinguistic Check-Points. COLING 2008: 1121-1128

·Lei Shi,Ming Zhou: ImprovedSentence Alignment on Parallel Web Pages Using a Stochastic Tree AlignmentModel. EMNLP 2008: 505-513

2007:

·GuihuaSun, Gao Cong, Xiaohua Liu, Chin-Yew Lin, Ming Zhou: MiningSequential Patterns and Tree Patterns to Detect Erroneous Sentences.AAAI 2007: 925-930

·Chi-HoLi, Minghui Li, Dongdong Zhang, Mu Li, Ming Zhou, Yi Guan: AProbabilistic Approach to Syntax-based Reordering for Statistical MachineTranslation. ACL 2007

·GuihuaSun, Xiaohua Liu, Gao Cong, Ming Zhou, Zhongyang Xiong, John Lee, Chin-Yew Lin:DetectingErroneous Sentences using Automatically Mined Sequential Patterns.ACL 2007

·QingChen, Mu Li, Ming Zhou: ImprovingQuery Spelling Correction Using Web Search Results.EMNLP-CoNLL 2007: 181-189

·JingjingLiu, Yunbo Cao, Chin-Yew Lin, Yalou Huang, Ming Zhou: Low-QualityProduct Review Detection in Opinion Summarization.EMNLP-CoNLL 2007: 334-342

·DongdongZhang, Mu Li, Chi-Ho Li, Ming Zhou: PhraseReordering Model Integrating Syntactic Knowledge for SMT.EMNLP-CoNLL 2007: 533-540

·JizhouHuang, Ming Zhou, Dan Yang: ExtractingChatbot Knowledge from Online Discussion Forums.IJCAI 2007: 423-428

·LongJiang, Ming Zhou, Lee-Feng Chien, Cheng Niu: NamedEntity Translation with Web Mining and Transliteration.IJCAI 2007: 1629-1634

·ShiqiZhao, Ming Zhou, Ting Liu: LearningQuestion Paraphrases for QA from Encarta Logs.IJCAI 2007: 1795-1801

·John Lee,Ming Zhou, Xiaohua Liu: Detectionof Non-Native Sentences Using Machine-Translated Training Data.HLT-NAACL (Short Papers) 2007: 93-96

·Wei Gao,Cheng Niu, Jian-Yun Nie, Ming Zhou, Jian Hu, Kam-Fai Wong, Hsiao-Wuen Hon: Cross-lingualquery suggestion using query logs of different languages.SIGIR 2007: 463-470

2006:

·JianfengGao, Jian-Yun Nie, Ming Zhou: Statisticalquery translation models for cross-language information retrieval.ACM Trans. Asian Lang. Inf. Process. 5(4): 323-359 (2006)

·Yi Chen,Ming Zhou, Shilong Wang: RerankingAnswers for Definitional QA Using Language Modeling.ACL 2006

·Mu Li,Muhua Zhu, Yang Zhang, Ming Zhou: ExploringDistributional Similarity Based Models for Query Spelling Correction.ACL 2006

·Lei Shi,Cheng Niu, Ming Zhou, Jianfeng Gao: A DOMTree Alignment Model for Mining Parallel Data from the Web.ACL 2006

2005:

·Kun Yu,Gang Guan, Ming Zhou: ResumeInformation Extraction with Cascaded Hybrid Model.ACL 2005

·Sung-HyonMyaeng, Ming Zhou, Kam-Fai Wong, HongJiang Zhang (Eds.): Information RetrievalTechnology, Asia Information Retrieval Symposium, AIRS 2004, Beijing, China,October 18-20, 2004, Revised Selected Papers. Lecture Notes in Computer Science3411, Springer 2005, ISBN 3-540-25065-4

2004:

·Ya-JuanLv,Ming Zhou, CollocationTranslation Acquisition Using Monolingual Corpora,42nd Annual Meeting of the Association for Computational Linguistics,Barcelona, Spain, Jul. 2004.

·Wei Wang,Ming Zhou: ImprovingWord Alignment Models using Structured Monolingual Corpora.EMNLP 2004: 198-205

·Dong-HuiFeng, Ya-Juan Lv, Ming Zhou,”A NewApproach for English-Chinese Named Entity Alignment”,2004 Conference on Empirical Methods in Natural Language Processing, Barcelona,Spain, Jul. 2004.

2003:

·Hua Wu,Ming Zhou: SynonymousCollocation Extraction Using Translation Information.ACL 2003: 120-127

·DekangLin, Shaojun Zhao, Lijuan Qin, Ming Zhou: IdentifyingSynonyms among Distributionally Similar Words.IJCAI 2003: 1492-1493

2002:

·Qing Ma,Min Zhang, Masaki Murata, Ming Zhou, Hitoshi Isahara: Self-OrganizingChinese and Japanese Semantic Maps. COLING2002

·Jian Sun,Jianfeng Gao, Lei Zhang, Ming Zhou, Changning Huang: ChineseNamed Entity Identification Using Class-based Language Model.COLING 2002

·Wei Wang,Ming Zhou, Jin-Xia Huang, Changning Huang: StructureAlignment Using Bilingual Chunking. COLING2002

·Jian-MinYao, Ming Zhou, Tiejun Zhao, Hao Yu, Sheng Li: AnAutomatic Evaluation Method for Localization Oriented Lexicalised EBMT System.COLING 2002

·JianfengGao, Ming Zhou, Jian-Yun Nie, Hongzhao He, Weijun Chen: Resolvingquery translation ambiguity using a decaying co-occurrence model and syntactic dependencerelations. SIGIR 2002: 183-190

2001:

·Wei Wang,Jin-Xia Huang, Ming Zhou, Changning Huang: FindingTarget Language Correspondence for Lexicalized EBMT System.NLPRS 2001: 455-460

·Tom B. Y.Lai, Changning Huang, Ming Zhou, Jiangbo Miao, Tony K. C. Siu: Span-basedStatistical Dependency Parsing of Chinese.NLPRS 2001: 677-684

·JianfengGao, Endong Xun, Ming Zhou, Changning Huang, Jian-Yun Nie, Jian Zhang: ImprovingQuery Translation for Cross-Language Information Retrieval Using StatisticalModels. SIGIR 2001: 96-104

2000:

·Ting Liu,Ming Zhou, Jianfeng Gao, Endong Xun, Changning Huang: PENS: A Machine-aided English WritingSystem for Chinese Users. ACL 2000

·EndongXun, Changning Huang, Ming Zhou: A Unified Statistical Model for theIdentification of English BaseNP. ACL2000

·LeiZhang, Ming Zhou, Changning Huang, Haihua Pan: Automatic Detecting/Correcting Errors inChinese Text by an Approximate Word-Matching Algorithm.ACL 2000

·Jian-YunNie, Jianfeng Gao, Jian Zhang, Ming Zhou: Onthe use of words and n-grams for Chinese information retrieval.IRAL 2000: 141-148

· Jianfeng Gao, Jian-Yun Nie, Jian Zhang,Endong Xun, Yi Su, Ming Zhou, Changning Huang: TREC-9CLIR Experiments at MSRCN. TREC 2000

2.4 InvitedTalks

1.    NLP lecture atChongqing University. 2018. PPT

2.    NLP Progress, methodand focus (in Chinese), Tsinghua University, 2018. PPT

3.    How to Do InterestingResearch (in Chinese), Turing Class, Peking University, 2018. PPT

4.    What Will SearchEngines be Changed by NLP Advancements. ICTIR 2018: 7. PPT

5.    NLP: Its progress,opportunities and challenges, CCF-AI, 2018.PPT

6.    Latest progress ofKB-QA, NLPCC 2018 QA Workshop. PPT

7.    Computer couplets,poetry and music (in Chinese). O’Reilly AI 2018, China. PPT

8.    NLP Progress at MSRA,EmTech 2018 Beijing. PPT

9.    Entertaining withWord Play-Computer Couplet, Poetry, Lyric and Riddle,  ROCLING 2016. PPT

New:I recently co-authored three books on NLP and AI:

1.    Machine Translation,High Education Publisher, 2018 （机器翻译，高教出版社，2018,简介）

2.    IntelligenceQuestion-Answering, High Education Publisher, 2018 （智能问答，高教出版社，2018，简介）

3.    Introduction to AI,Science Publisher, 2018  （人工智能导论，科学出版社，2018，简介

(赞赏后下载本文PDF和上述invited talks 9 PPT的ZIP包)

©Microsoft2019(注：资料来自微软亚洲研究院[1-2])

免责说明：资料来自微软亚洲研究院。文章只为学术新闻信息传播，注明出处文字参考文献可溯源。本公众号不持有任何倾向性，亦不表示认可其观点或其所述。

转载本公号文章请注明出处、作者、时间等信息，如“此文转自©微信公号：数据简化DataSimp，作者：秦陇纪，时间：2016.3.15Tue”字样，详情邮件咨询QinDragon2010@qq.com，转载请保留本信息。本公号保留相应版权，如有引文/译注/出处不明或遗漏/版权问题等，请给公号发留言或邮件到DataSimp@126.com。欢迎数据科学和人工智能学界、产业界同仁赐稿，投稿邮箱DataSimp@126.com，范围：AI/语言处理/数据/智能等科学技术论文。

数据DataSimp社区分享：信息与数据处理分析、数据科学研究前沿、数据资源现状和数据简化基础的科学知识、技术应用、产业活动、人物机构等信息。欢迎大家参与投稿，为数据科学技术做贡献，使国人尽快提高数据能力，提高社会信息流通效率。做事要平台，思路要跟进；止步吃住行，无力推文明。要推进人类文明，不可止步于敲门呐喊；设计空想太多，无法实现就虚度一生；工程能力至关重要，秦陇纪与君共勉之。

—END—

---

参考文献(559字)

1. 周明, Microsoft. 如何在NLP领域第一次做成一件事.[EB/OL]; 微软亚洲研究院, https://www.msra.cn/zh-cn/news/features/nlp-20161124, 2016-11-24, visitingdata: 2019-01-13.

2. 周明, Microsoft.周明.[EB/OL]; 微软亚洲研究院, https://www.msra.cn/zh-cn/people/ming-zhou,visiting data: 2019-01-13.

3. Microsoft. Ming Zhou.[EB/OL]; Microsoft,https://www.microsoft.com/en-us/research/people/mingzhou/, visiting data:2019-01-13.

x.秦陇纪．数据简化社区Python官网Web框架概述；数据简化社区2018年全球数据库总结及18种主流数据库介绍；数据科学与大数据技术专业概论；人工智能研究现状及教育应用；信息社会的数据资源概论；纯文本数据溯源与简化之神经网络训练；大数据简化之技术体系．[EB/OL]；数据简化DataSimp(微信公号)，http://www.datasimp.org，2017-06-06．

---

秦陇纪©2010-2019数据简化DataSimp

简介：如何在NLP领域做成一件事by周明ACL计算语言学会候任主席。作者：周明，微软亚洲研究院副院长。来源：微软亚洲研究院/数据简化社区/秦陇纪微信群聊公众号，参考文献附引文出处。公号输入栏回复关键字“NLP做事”或文末链接“阅读原文”可下载本文38k字9图16页PDF资料；标题下蓝链接“数据简化DataSimp”关注后，菜单项有文章分类页。版权声明：科普文章仅供学习研究，公开资料©版权归原作者，请勿用于商业非法目的。秦陇纪2010数据简化DataSimp综合汇译编，投稿合作、转载授权/侵权、原文引文错误等请联系DataSimp@126.com沟通。主编译者：秦陇纪，数据简化DataSimp/科学Sciences/知识简化新媒体创立者，数据简化社区创始人，数据简化OS设计师/架构师，ASM/Cs/Java/Python/Prolog程序员，英语/设计/IT教师。每天大量中英文阅读/设计开发调试/文章汇译编简化，时间精力人力有限，欢迎支持加入社区。社区媒体：“数据简化DataSimp、科学Sciences、知识简化”新媒体聚集专业领域一线研究员；研究技术时也传播知识、专业视角解释和普及科学现象和原理，展现自然社会生活之科学面。秦陇纪发起，期待您参与各领域；欢迎分享、赞赏、支持科普~~

---

Appx(1236字).数据简化DataSimp社区简介

信息社会之数据、信息、知识、理论持续累积，远超个人认知学习的时间、精力和能力。必须行动起来，解决这个问题。应对大数据时代的数据爆炸、信息爆炸、知识爆炸，解决之道重在数据简化(Data Simplification)：简化减少知识、媒体、社交数据，使信息、数据、知识越来越简单，符合人与设备的负荷。(秦陇纪，2010)

数据简化DataSimp年度会议(DS2010-2019)，聚焦数据简化技术(Data Simplification Techniques)：对各类数据从采集、处理、存储、阅读、分析、逻辑、形式等方面做简化，应用于信息及数据系统、知识工程、各类数据库、物理空间表征、生物医学数据，数学统计、自然语言处理、机器学习技术、人工智能等领域。欢迎数据科学技术、简化实例相关论文投稿加入数据简化社区，参加会议出版专著。请投会员邮箱DataSimp@163.com，详情访问社区网站www.datasimp.org。填写申请表加入数据简化DataSimp社区成员，应至少有一篇数据智能、编程开发IT文章：①原创数据智能科技论文；②数据智能工程技术开源程序代码；③翻译美欧数据智能科技论文；④社区网站发帖人管理员版主志愿者义工；⑤完善黑白静态和三彩色动态社区S圈型LOGO图标。DataSimplification/Sciences/Knowledge Simplification Public Accounts——DataSimp@163.com, 2018.12.12Wed,Xi'an, Shaanxi, China.

LIFE

Life begins at the end of your comfortzone.——Neale Donald Walsch

THE DAY

The strength of purpose and the clarity ofyour vision，alongwith the tenacity to pursue it，is your underlying driver ofsuccess.——Ragy Tomas

投稿QQ群223518938数据简化DataSimp社区；技术公众号“数据简化DataSimp”留言，或(备注：姓名/单位-职务/学校-专业/手机号)加微信账号QinlongGEcai，进“数据简化DataSimp社区”投稿群或“科学Sciences学术文献”读者群等群聊。关注如下三个公众号(搜名称也行)，关注后底部菜单有文章分类页链接。

数据技术公众号“数据简化DataSimp”：

科普公众号“科学Sciences”：

社会教育知识公众号“知识简化”：

(转载请写出处：©数据简化DataSimp2010-2018汇译编，欢迎技术、传媒伙伴投稿、加入数据简化社区！“数据简化DataSimp、科学Sciences、知识简化”投稿反馈邮箱DataSimp@126.com。)

普及科学知识，分享到朋友圈

转发/留言/打赏后“阅读原文”下载PDF