個人資料 (Personal Information)

Jing-Shin Chang (張景新)			Last Update: 2018/06/01

Major Research Fields:

	- Machine Translation, Corpus-Based Statistics-Oriented Approaches
	- Probabilistic Models for Natural Language Processing
	- Web Information Processing & Applications
	- Lexicon Acquisition and Precision-Recall Maximization
	- CJK Language Processing Technologies

		- Lexical: automatic lexicon/term acquisition
		- Syntactic: probabilistic parsing
		- Semantic: generalized probabilistic semantic model (GPSM)
		- Transfer & Generation: corpus-based statistics-oriented transfer and generation model 

	- NMT: Neural Machine Translation

	- LLM: Large Language Models (for Machine Translation, Chatbot, and various NLP Tasks)

	- Languages: Taiwanese, Mandarin Chinese, English, Japanese (a little bit Korean, French, ...)

專長及相關研究:

	- 機器翻譯系統 (Machine Translation Systems) [click here for a local link]
		- 自然語言剖析器 (Parser) 設計
		- 詞彙、句法及語意分析之數理模式 (Corpus-Based Statistics-Oriented 
			Approaches for Lexical, Syntax and Semantics Analyses)
		- 機器翻譯系統生成、轉換模組之數理模式 (Corpus-Based Statistics-Oriented 
			Approaches for Transfer and Generation in Machine Translation)
		- 統計式機器翻譯模型之簡縮 (Model Pruning of SMT)
			- 翻譯模型之簡縮 (Translation Model Pruning)
			- 語言模型之簡縮 (Language Model Pruning)
		- NMT (神經網路機器翻譯模型)
		- LLM-MT (大語言模型之機器翻譯任務)

	- 自然語言處理 (Natural Language Processing) 樣型識別 (Pattern
		Recognition & Classification) 及人工智慧 (Artificial 
		Intelligence)

	- 資訊檢索最佳化技術 (Optimization on Information Retrieval)
		- Precision-Recall Joint Optimization 及自動學習技術
		- 電子詞彙自動抽取 (Automatic Lexicon/Compound Word Extraction)
		- 新詞/未知詞抽取 (New/Unknown Word Extraction)
		- 引導式與非引導式詞彙自動建構及自動學習 (Supervised/Unsupervised 
			Approaches for Lexicon Extraction)
		- LLM as a Generative Finite State Search Engine
			- 以生成式有限狀態機搜尋引擎觀點為基礎的大語言模型最佳化理論

	- 中文資訊處理 (Chinese Information Processing): 斷詞及詞彙、句法及語意分析
		- 中文縮寫詞 (abbreviation) 之生成 (generation) 與復原 (recovery)

System Development:

	- was the principle designer of the parser for the
		ArchTran/BehaviorTran Machine Translation System,
		of the NTHU NLP LAB & the Behavior Design Corp.:

		- Generalized LR Parser, mixing Bottom-Up Parsing
			and Top-Down Filtering parsing capabilities
			for efficient parsing

		- Support Scored Truncation for Objectively Disambiguate
			Ambiguities

		- Support Partition of Grammars into Sub-grammars for
			Sub-sentence element parsing

Community Services:

    - Executive Board Member
	- ROCLING/ACLCLP Executive Board Member (8th~12th, 15th terms, 2003/09~2013/09, 2017/09~2019/09)
		- 中華民國計算語言學學會理事 (第八~十二屆, 第十五屆 2003/09~2013/09, 2017/09~2019/09)

	- ROCLING/ACLCLP Alternate Executive Board Member (13th~14th terms, 2013/09~2017/09)
		- 中華民國計算語言學學會候補理事 (第十三~十四屆, 2013/09~2017/09)

	- AFNLP Delegate of AFNLP Regional Association Board for ACLCLP (2009-)
		- AFNLP (Asian Federation of Natural Language Processing)
		- ACLCLP (Association for Computational Linguistics and Chinese Language Processing)

	- ACL Executive Board Member & Chief Information Officer (2016-2018) news-1 news-2 news-3
	- ACL Executive Board Member & Chief Information Officer (2016-2018) news-1 news-2 news-3 about elec-2016 elec-2017 wiki-1(Local copy)

    - Editorial Board
	- NLP Section Editor, International Journal of Computational Linguistics and Chinese Language Processing (IJCLCLP)
	- 2008/05 ~ 2012/04

    - Program Committee & Chair:

	- EMNLP/VLC-99
		JOINT SIGDAT CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE
		PROCESSING AND VERY LARGE CORPORA,

		SIGDAT (Special Interest Group for Linguistic Data and Corpus-based
		Approaches to NLP), Association for Computational Linguistics,
		University of Maryland, June 21-22, 1999.

	- ROCLING 2000 (and more...)
		Research on Computational Linguistics Conference XIII,
		National Taiwan University, Taipei, 24-25 August, 2000.

	- PACLIC 15 (2001)
		THE 15TH PACIFIC ASIA CONFERENCE ON
		LANGUAGE, INFORMATION AND COMPUTATION (PACLIC 15)
		1 - 3 February 2001, City University of Hong Kong

	- NLPRS-01 (2001)
		NLPRS 2001, 6th Natural Language Processing
		Pacific Rim Symposium, 27 - 29 November, 2001
		National Center of Science, Tokyo, Japan

	- COLING-2002 (Local Organization)
		The 19th International Conference on Computational Linguistics,
		ICCL, Aug. 26-30, 2002, Academia Sinica, Taipei, Taiwan.
		(Tutorials: 24-25, August, Workshop: 08/31-09/01)

	- COLING-2002 Tutorial Program (Co-Chair)

	- IJCNLP-08 (Publication Chair)
		The Third International Joint Conference on Natural Language Processing
		AFNLP, January 7-12, 2008, Hyderabad, India

	- ACL-IJCNLP-09 (Publication Co-Chair)
		The Joint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and 
		the 4th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing
		ACL & AFNLP, 2-7 August, 2009, Singapore.

	- ACL-2010 (Publication Co-Chair)
		The 48th Annual Meeting of the Association for Computational Linguistics,
		Uppsala, Sweden, July 11–16, 2010.

	- ROCLING-2010 (Conference Chair)
		The 22nd International Conference on Computational Linguistics and Speech Processing, ROCLING-2010,
		National Chi Nan University, Puli, Nantou, Taiwan, ROC, September 1-2, 2010.

	- PACLIC-24 (PC Member)
		The 24th Pacific Asia Conference on Language, Information and Computation (PACLIC 24)
		Tohoku University, Sendai, Japan, November 4-7, 2010.

	- ACL-2013 (Publication Co-Chair)
		The 51st Annual Meeting of the Association for Computational Linguistics,
		Sofia, Bulgaria, August 4-9, 2013.

	- PACLIC-27 (Publication Chair)
		The 27th Pacific Asia Conference on Language, Information and Computation (PACLIC 27)
		National Chengchi University, Taipei, Taiwan, November 21-24, 2013.

	- COLING-2014 (Area Chair of Software & Tools)
		The 25th International Conference on Computational Linguistics,
		ICCL, Dublin City University (DCU), Ireland, August 23-29, 2014.

	- ACL-IJCNLP-2021 (Publication Co-Chair)
		The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and
		the 10th International Joint Conference on Natural Language Processing (ACL-IJCNLP 2021),
		ACL & AFNLP, 1-6 August, 2021, Thailand.

	- (More ...)

    - Journal and Conference Paper Review:

	- ROCLING Conferences

	- ACL '99: the 37th Annual Meeting of the Association for
		Computational Linguistics, Univ. of Maryland, 1999.

	- EMNLP/VLC-99, Univ. of Maryland, 1999.

	- International Journal of Computational Linguistics
		& Chinese Language Processing (CLCLP), Academia Sinica, Taipei, 1999.

	- Journal of Computer Processing of Oriental Languages

	- ACM Transactions on Asian Language Information Processing (TALIP)

	- JNLE (Journal of Natural Language Engineering)

	- MLJ (Machine Learning Journal)

	- JISE (Journal of Information Science and Engineering)

	- JEB (Journal of e-Business)

	- LRE (Language Resources and Evaluation), 2006

	- ACL-07
		- Phonology/Morphology/Finite-State Technology
			/Tagging/Word Segmentation track

	- More...

    - Lectures/Tutorial Courses/Invited Talks

	- [1] Unsupervised Learning for Natural Language Processing
		- ROCLING/ACLCLP, Academia Sinica, Taipei, Taiwan, ROC., 12/10/1999.
		- Co-lecture with Dr. Keh-Yih Su.


	- [2] Lecture for Statistical Natural Language Processing (at Microsoft Research Asia, MSRA)
		- an Open Tutorial for Academic Institutes
			- Microsoft Research Asia (微軟亞洲研究院), Beijing, PRC, Aug 17-18, 2002
			- Microsoft Research Asia (微軟亞洲研究院) Lecture News (local copy)
			- Summer Tutorial on Statistical Natural Language Processing, Beijing, PRC, Aug 17-18, 2002
			- Summer Tutorial on Statistical Natural Language Processing, (local copy)
			
		- Co-lecture with Prof./Dr. Keh-Yih Su.
			- Lecture Slides: in compressed PDF [.PDF.zip]
			- Book Cover [.jpg]
			(Some minor typos are known in the current version. Fixes are being made.
			 Any correction is appreciated.)

	- [3] Automatic Lexicon Acquisition (with Precision-Recall Maximization Techniques)
		- invited talk, SWCL-2002 (1st Student Workshop on Computational Linguiatics), (at Peking University, PKU)
		- SWCL-2002
		- SWCL-2002 program schedule (local copy, HTML)
		- SWCL-2002 program schedule (local copy, PDF)
		- SWCL-2002 Workshop Slides
			- Peking University, Beijing, PRC, Aug 21, 2002

	- [4] Pitfalls in Applying Unsupervised Learning to NLP
		- Pre-Conference Tutorial, IJCNLP-04, Mar 21, 2004
			- IJCNLP-04, Sanya, Hainan, PRC, Mar 22-24, 2004
		- Jing-Shin Chang and Keh-Yih Su.
		- Tutorial Slides: in compressed PDF (.PDF.zip)

	- [5] Mining Domain Specific Words from Web Documents
		- 4-th China-Japan Joint Conference to Promote Cooperation in Natural Language Processing
		- CJNLP-04, 10-15 Nov. 2004, City Univ. of Hong Kong

	- [6] TIGP NLP Course: Statistical Methods for Natural Language Processing
		- Taiwan International Graduate Program
		- Joint Program for international graduate students
		- by Academia Sinica, Taipei, and National Tsing-Hua University, Hsinchu
		- 2005/11, 2006/11

	- [7] Statistical Models for Chinese Abbreviations
		- 6-th China-Japan Joint Conference to Promote Cooperation in Natural Language Processing
		- CJNLP-06, 2006/11/13~15, Shanghai Jiao Tong University (SJTU)


	- [*] Jing-Shin Chang, "Chinese New Lexicon Identification and English Compound Word Extraction"
		Workshop on Electronic Dictionary, Machine Translation and Information Retrieval,
		ROC Computational Linguistics Society, 1997 Q2, Academia Sinica, Taipei, ROC, Jun 2nd, 1997.

	- [*] Jing-Shin Chang, "A Proposed Tag Set for Exchanging Word-Segmented
		Text Corpora", Public Hearing on the "Word Segmentation Standard
		for Chinese Data Processing" Project ([中文資料處理分詞規範計畫]公聽會),
		hosted by the ROC Computational Linguistics Society (sponsored
		by the National Bureau of Standard, Ministry of Economy),
		Academia Sinica, Taipei, ROC, May 29, 1998.

研究方向:

	- 自然語言模式之建構與 Internet 資訊擷取應用 (Language Modeling)
		- 機器翻譯
		- 與 Internet 結合之跨語言(英中日)資訊擷取技術 (Multi-lingual
			Information  Extraction)
		- 文件自動摘要技術 (Text Summarization)
		- 中文詞彙、句法及語意分析 (Chinese Lexical, Syntax, Semantics Analyses)
		- 多語言電子詞彙自動建構 (Multi-lingual Lexicon Extraction)
		- 跨語言文法擷取與轉換 (Multi-lingual Grammar Extraction and 
			Transformation)

	- 語言模式之參數估測 (Parameter Learning for Language Models)
		- Information Retrieval 之 Precision-Recall 綜合強化技術及自動學習技術
		- 強健性的自然語言處理技術 (Robustness-Oriented NLP Techniques)
		- 非引導式之自然語言自動學習技術 (Unsupervised Learning Approaches
			for NLP Applications)

Publication List