張華平中科院計算技術(shù)研究所Emailzhanghp@software.ict.ac

1、張華平 中科院計算技術(shù)研究所Email:Homepage:pipy_;2002-9-52COLING2002綜述 2002-9-5 張華平綱要 COLING會議的背景和歷史 COLING2002的日程及概述 SIGHAN介紹 收錄論文概述 簡述幾篇文章 當(dāng)前研究熱點(diǎn)分析 胡亂點(diǎn)評3COLING2002綜述 2002-9-5 張華平COLING會議的背景和歷史 The most prominent conference in the field of Computational Linguistics. Main biennial international conference in comp

2、utational linguistics. A productive forum for scholars all over the world to exchange original research papers on a broad range of topics in computational linguistics. COLING is an international forum for discussion and presentation representing the current state of the art and determining standards

3、 of computational linguistics research. 4COLING2002綜述 2002-9-5 張華平COLING會議的背景和歷史(Cont.) Administrator: ICCL (International Committee on Computational Linguistics) 19 Conferences since 1956, holding every 2 years. www.dcs.shef.ac.uk/research/ilash/iccl/5COLING2002綜述 2002-9-5 張華平COLING會

4、議的背景和歷史(Cont.) 1965 New York 1967 Grenoble 1969 Stockholm 1971 Debrecen 1973 Pisa 1976 Ottawa 1978 Bergen 1980 Tokyo 1982 Prague 1984 Stanford 1986 Bonn 1988 Budapest 1990 Helsinki 1992 Nantes 1994 Kyoto 1996 Copenhagen 1998 Montr閍l 2000 Saarbruecken 2002 Taipei6COLING2002綜述 2002-9-5 張華平COLING會議的背景和

5、歷史(Cont.) COLING2002的狀況 the first time that COLING is held outside Europe, North America, or Japan. Over 450 researchers from about 45 countries. About 180 Chinese speakers; 40 persons with PRC VISA; 20 ones directly from PRC. President of Academia Sinica;President of ICCL; Mayor of Taipei7COLING200

6、2綜述 2002-9-5 張華平COLING2002的日程及概述 Tutorials(8.24-8.25) Open Ceremony(8.26) Keynotes Speeches (8.26) Sessions I(8.26-8.27) Excursion 8.28 Sessions II(8.29-8.30) Keynotes Speech Discussion Panel Workshop(8.31-9.1)8COLING2002綜述 2002-9-5 張華平Tutorials (8.24-8.25) Intelligent Character System 莊德明莊德明 謝清俊謝清俊

7、 Corpus-Based Methods in Chinese Morphology Richard Sproat (AT&T Labs.) Treebanking and Parsing Keh-Jian Chen Open-Domain Textual Question and Answering Sanda Harabagiu and Dan Moldovan (Humain Language Tech. Research Inst. University of Texas)9COLING2002綜述 2002-9-5 張華平Main Conference(8.26-8.30)

8、 Open Ceremony Yuan T. Lee(李遠(yuǎn)哲): President of Academia Sinica Martin Kay: President of ICCL COMPUTER MODELING OF LANGUAGE EVOLUTION William S-Y.Wang and Jinyun Ke, City University of Hong Kong New Chances for Deep Linguistic ProcessingHans USZKOREIT, Language Technology Lab,German Research Center fo

9、r Artificial Intelligence and Saarland University10COLING2002綜述 2002-9-5 張華平Main Conference(8.26-8.30) Reception ar Chungshan Hall Mayor Yin-Jeou Ma (Ph. D of Politics, Harvard). Sessions 30 topics 60 Sessions 19 Projects 197 papers 10 workshops 11COLING2002綜述 2002-9-5 張華平 介紹 a Special Interest Grou

10、p of the Association for Computational Linguistics First international organization for Chinese Language Processing. Established in 2002.3 Chair: Martha PALMER University of Pennsylvania;Vice-Chair/Treasurer Richard SPROAT AT&T Labs 被認(rèn)為是中文自然語言處理里程碑事件之一12COLING2002綜述 2002-9-5 張華平收錄論文概述 理論與方法： Gen

11、eration (6) Parsing Methods (12) Grammar Formalisms (3) Morphology (6) Tagging (3) Unification Based Grammars (6) Semantics (6)13COLING2002綜述 2002-9-5 張華平收錄論文概述(Cont.) 理論與方法： Probabilistic Models (3) Ontology (3) Corpus Linguistics (6) Computational Lexicons (5) Bilingual Corpora (3) Word Order (3)1

12、4COLING2002綜述 2002-9-5 張華平收錄論文概述(Cont.) 應(yīng)用與系統(tǒng) Question-Answering(9) Language Engineering (3) Information Extraction(9) Machine Translation (12) Learning Systems (9) Spoken Dialog Systems (6) Information Retrieval (6) Multi Topic (6)15COLING2002綜述 2002-9-5 張華平收錄論文概述(Cont.)應(yīng)用與系統(tǒng) Discourse Analysis (3)

13、 Text Classification and Categorization (6) Speech (3) Oriental Language Processing (6) Summarization (3) Terminology Identification (3) Word Sense Disambiguation (9) Named Entity Recognition (6)16COLING2002綜述 2002-9-5 張華平收錄論文概述(Cont.) Workshop SEMANET: Building and Using Semantic Networks The 3rd W

14、orkshop on Asian Language Resources and International Standardization A Roadmap for Computational Linguistics COMPUTERM 2002: Second International Workshop on Computational Terminology Multilingual Summarization and Question Answering The 6th Conference on Natural Language Learning 2002 (CoNLL-2002)

15、 Grammar Engineering and Evaluation17COLING2002綜述 2002-9-5 張華平收錄論文概述(Cont.) Workshop Machine Translation in Asia The 2nd Workshop on NLP and XML (NLPXML-2002) The First SIGHAN Workshop on Chinese Language Processing Multilingual Summarization and Question Answering The 6th Conference on Natural Lang

16、uage Learning 2002 (CoNLL-2002)18COLING2002綜述 2002-9-5 張華平簡述幾篇文章 Intelligent Character Encoding莊德明莊德明 謝清俊謝清俊字元+Operators 朱邦福：漢字基因（倉頡碼發(fā)明人）19COLING2002綜述 2002-9-5 張華平簡述幾篇文章(Cont) Investigating the Relationship between Word SegmentationPerformance and Retrieval Performance in Chinese IRFuchun Peng20COL

17、ING2002綜述 2002-9-5 張華平簡述幾篇文章(Cont) Combining Classifiers for Chinese Word Segmentation Nianwen Xue Susan P. Converse 21COLING2002綜述 2002-9-5 張華平簡述幾篇文章(Cont) PCFG Parsing for Restricted Classical Chinese Texts Liang HUANG Yinan PENG Corpus-Based Pinyin Name Resolution Kui-Lam KWOK Peter DENG22COLING2

18、002綜述 2002-9-5 張華平當(dāng)前研究熱點(diǎn)分析Top 6 topics: Machine Translation (12)+1 workshop Parsing Methods (12) Question-Answering(9) +2 workshops Word Sense Disambiguation (9) +1 workshop Information Extraction(9) Learning Systems (9) 以下推斷，純屬臆測，如有雷同，或有不對，恕難負(fù)責(zé)！23COLING2002綜述 2002-9-5 張華平當(dāng)前研究熱點(diǎn)分析(Cont.) 亞洲語言(特別是中文)

19、成為研究的重點(diǎn) 19 papers directly research in Chinese; 1 workshop (20 papers) purely in Chinese Language Processing 2 other workshop is related to Asian language processing; Over 30 papers are related to Asian language, five of them is about Japanese Many researchers in Chinese language processing are not native Chinese speaker,such as American, Korea, Netherlands, Japan. Some famous groups from U of Penn., AT&T.24COLING2002綜述 2002-9-5 張華平當(dāng)前研究熱點(diǎn)分析(Cont.) 語義的研究成為熱門 Papers using WordNet are huge; In 3 Keynote speeches: one for semantics