Chun Yu KIT's Home Page

A man can succeed at almost anything for which he has unlimited enthusiasm.

-- Charles M. Schwab

Chunyu KIT (Official homepage)

Associate Professor
PhD (Sheffield), MSc (CMU), MPhil (CPHK), MA (CASS), BEng (Tsinghua)

Department of Chinese, Translation & Linguistics, City University of Hong Kong,
|| Rm: B7608 || Tel.: +852 2788 9310 (O), 9380 1738 (M), +86 136 5881 2972 ||
|| Fax: (+852) 2788 8706, 2788 8720 || Email: ctckit @ cityu.edu.hk ||

|| Teaching || Research || Publications || Education || Poetry ||

Research Interests: Computational linguistics, computational poetry/poetics, computational terminology, machine translation, machine learning of natural language, Chinese poetry, ...

Teaching: Computational linguistics, language technology, machine translation, corpus linguistics, general linguistics, Chinese computing, parsing, text processing & information retrieval, ...

Publications

2010

Chunyu Kit. 2010. Recent advances in computational linguistics. A book chpater to appear in Jenny Z. J. Wang and Dongdong Chen (eds.), Lingusitics, pp.??-??. China Remin University Press.
Hai Zhao and Chunyu Kit. 2010. Integrating unsupervised and supervised word segmentation: The role of goodness measures. Accepted to Information Sciences, 180(?):??-?? (forthcoming). Elsevier.
Yan Song, Chunyu Kit and Hai Zhao. 2010. Reranking with Multiple Features for Better Transliteration , to appear in Named Entities Workshop (NEWS) 2010, pp.??-??. Uppsala, July 16, 2010.
Billy Wong and Chunyu Kit. 2010. The Parameter-optimized ATEC Metric for MT Evaluation. To appear in the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR, pp. ??-??. Uppsala, July 15–16, 2010.
Ruifeng Xu, Jun Xu and Chunyu Kit. 2010. HITSZ_CITYU: Combine collocation, context words and neighboring sentence sentiment in sentiment adjectives disambiguation. To appear in the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR, pp. ??-??. Uppsala, July 15–16, 2010.
Yan Song and Chunyu Kit. 2010. Does joint decoding really outperform cascade processing in English-to-Chinese transliteration generation? The role of syllabification. To appear in the Proceedings of the International Conference on Machine Learning and Cybernetics (ICMLC) 2010, pp.??-??. Qingdao, July 11-14, 2010.
Billy Wong and Chunyu Kit. 2010. ATEC: automatic evaluation of machine translation via word choice and word order. Machine Translation, 23(2):141-155. Springer. DOI: 10.1007/s10590-009-9061-x.

2009

Ruifeng Xu and Chunyu Kit. 2010. Incorporating multi level features for sentiment analysis. In Proceedings of Second Chinese Opinion Anlaysis Evaluation Workshop (COAE2009), pp.74-82. Shanghai, November, 2009
Xiao Chen, Changning Huang, Mu Li and Chunyu Kit. 2009. Better parser combination. In Proceedings of CIPS-ParsEval-2009, pp.81-90. Beijing, Nov. 10, 2009.
Yan Song and Chunyu Kit. 2009. PCFG parsing with CRF tagging for head recognition. In Proceedings of CIPS-ParsEval-2009, pp.133-137. Beijing, Nov. 10, 2009.
Yan Song, Chunyu Kit and Xiao Chen, 2009. Transliteration of Name Entity via Improved Statistical Translation on Character Sequences. In Proceedings of the 2009 Named Entities Workshop: Shared Task on Transliteration (NEWS 2009), pp.57-60. Suntec, Singapore, 7 August, 2009.
Hai Zhao, Wenliang Chen, Chunyu Kit. 2009. Semantic dependency parsing of NomBank and PropBank: An efficient integrated approach via a large-scale feature selection. In EMNLP 2009: Conference on Empirical Methods in Natural Language Processing, pp.30-39. Singapore, August 6-7, 2009.
Hai Zhao, Yan Song, Chunyu Kit and Guodong Zhou. 2009. Cross Language Dependency Parsing using a Bilingual Lexicon, in ACL-IJCNLP 2009, pp.55-63. Singapore, 3-5 August, 2009.
Hai Zhao, Chunyu Kit, and Yan Song. 2009. Character dependency tree based lexical and syntactic all-in-one parsing for Chinese, in Maosong Sun and Qunxiu Chen (eds.) Advances in computational linguistics in China, theProceedings of the 10th Chinese National Conference on Computational Linguistics (CNCCL-2009), pp. 82-88. Yantai, China, July 24-26, 2009. (in Chinese)
Xiaoyue Liu and Chunyu Kit. 2009. Statistical term-hood measurement for mono-word terms via corpus comparison. In 2009 International Conference onMachine Learning and Cybernetics (ICMLC 2009), Vol. 6, pp.2499-3504. Baoding, Hebei, China, July 12-15, 2009.
Ruifeng Xu and Chunyu Kit. 2009. Corse-fine strategy in opinion mining. In 2009 International Conference on Machine Learning and Cybernetics (ICMLC 2009), Vol. 6, pp.3469-3474. Baoding, Hebei, China, July 12-15, 2009.
Yan Song, Chunyu Kit, Ruifeng Xu and Hai Zhao. 2009. How unsupervised learning affects character tagging based Chinese word segmentation: A quantitative investigation. In 2009 International Conference on Machine Learning and Cybernetics (ICMLC 2009), Vol. 6, pp.3481-3486. Baoding, Hebei, China, July 12-15, 2009.
Hai Zhao, Wenliang Chen, Chunyu Kit, and Guodong Zhou. 2009. Multilingual Dependency Learning: A huge feature engineering method to semantic dependency parsing, in Proceedings of 13th Conference on Computational Natural Language Learning (CoNLL 2009): Shared task, pp. 55-60. Boulder, CO, USA, June 4-5, 2009
Chunyu Kit and Zhiwei Feng. 2009. Ontology-based Definition of Term. Terminology Standardization & Information Technology, 2009 Issue 02, pp.4-8 (part 1) , Issue 03 pp.14-23 (part 2).
Hai Zhao and Chunyu Kit. 2009. A Simple and Efficient Model Pruning Method for Conditional Random Fields. In Proceedings of the 22nd International Conference on the Computer Processing of Oriental Languages (ICCPOL-2009), pp.149-159. Hong Kong, March 26-27, 2009. Springer. PDF (236.8 KB)
Xiaoyue Liu, Jonathan Webster, and Chunyu Kit. 2009. An Extractive Text Summarizer Based on Significant Words. In Proceedings of the 22nd International Conference on the Computer Processing of Oriental Languages (ICCPOL-2009), pp.172-182. Hong Kong, March 26-27, 2009. Springer. PDF (184.5 KB)
Billy T-M Wong and Chunyu Kit. 2009. Meta-Evaluation of Machine Translation on Legal Texts. In Proceedings of the 22nd International Conference on the Computer Processing of Oriental Languages (ICCPOL-2009), pp.343-350. Hong Kong, March 26-27, 2009. Springer. PDF (190.1 KB)

2008

Chunyu Kit and Xiaoyue Liu. 2008. Measuring mono-word termhood by rank difference via corpus comparison. Terminology, 14(2):204-229. (December 2008)
Liu, Xiaoyue and Kit, Chunyu. 2008. An Improved Corpus Comparison Approach to Domain Specific Term Recognition, in Proceedings of the 22nd Pacific Asia Conference on Language, Information, and Computation (PACLIC 22), pp. 253-261. De La Salle Univ, Cebu, Philippines, Nov. 20-22, 2008
Billy T-M Wong and Chunyu Kit. Word choice and word position for automatic MT evaluation. AMTA 2008 Workshop: MetricsMATR, Waikiki, Hawai'i, October 25, 2008. Also, see NIST Metrics for Machine Translation 2008 Evaluation (MetricsMATR08).
Hai Zhao and Chunyu Kit. 2008. Parsing Syntactic and Semantic Dependencies with Two Single-Stage Maximum Entropy Models, in Proceedings of 12th Conference on Computational Natural Language Learning (CoNLL-2008), pp.203-207, Manchester, UK, August 16-17, 2008
Hai Zhao, and Chunyu Kit. 2008. Scaling Conditional Random Fields by One-against-the-Other Decomposition. Journal of Computer Science and Technology, 23(4):612-619 (July 2008). Springer. PDF (320.0 KB)
Guohong FU, Chunyu KIT and Jonathan WEBSTER. 2008. A Morpheme-based Lexical Chunking System for Chinese. In Proceedings of the 7th International Conference on Machine Learning and Cybernetics (ICMLC 2008), pp 2455-2460, Kunming, China, 12-15 July 2008.
Guohong Fu, Chunyu Kit, and Jonathan J. Webster. 2008. Chinese word segmentation as morpheme-based lexical chunking. Information Sciences, 178(9):2282-2296. (1 May 2008)
Chunyu Kit and Tak Ming Wong. 2008. Comparative evaluation of online machine translation systems with legal texts. Law Library Journal, 100(2):299-321. (Spring 2008)
Hai Zhao and Chunyu Kit. 2008. Exploiting Unlabeled Text with Different Unsupervised Segmentation Criteria for Chinese Word Segmentation. Research in Computing Science, Vol. 33, pp.93-104. March 2008
Risong Na, Chunyu Kit, and Zhiwei Feng. 2008. Statistical analysis of legal terms in Hong Kong bilingual laws information system. Terminology Standardization and Information, 2008 Issue 02, pp.32-35. February 2008. (in Chinese)
Hai Zhao and Chunyu Kit. 2008. Unsupervised segmentation helps supervised learning of word segmentation and named entity recognition. In Proceedings of the Sixth SIGHAN Workshop on Chinese Language Processing (SIGHAN-6), pp.106-111. Hyderabad, India, 11-12 January 2008.

Hai Zhao and Chunyu Kit. 2008. An empirical comparison of goodness measures for unsupervised Chinese word segmentation with a unified framework. In Proceedings of the Third International Joint Conference on Natural Language Processing (IJCNLP-08), Vol. 1, pp.9-16. Hyderabad, India, 7-12 January, 2008.
Chunyu Kit, Hio Tong Chan, and Xiaoyue Liu. 2008. Encoding hierarchical bilingual Texts of Hong Kong laws with XCES. In ICGL 2008: The First International Conference on Global Interoperability for Language Resources, pp.130-137. City University of HK.

2007

Chunyu Kit and Jessica Y. H. Ng. 2007. An intelligent Web agent to mine bilingual parallel pages via automatic discovery of URL pairing patterns. In 2007 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology - Workshops: Workshop on Agents and Data Mining Interaction (ADMI-07), pp.526-529. Silicon Valley, California, November 2-5, 2007,.

Hai Zhao and Chunyu Kit. 2007c. Incorporating global information into supervised learning for Chinese word segmentation. To appear in the Proceedings of the 2007 Conference of the Pacific Association for Computational Linguistics (PACLING 2007), pp.66-74, University of Melbourne, Australia, September 19-21, 2007

Hai Zhao and Chunyu Kit. 2007b. Scaling conditional random field with application to Chinese word segmentation. In Third International Conference on Natural Computation (ICNC'07), Vol. 5, pp.95-99. Haikou, China. Aug. 24-27, 2007.

Hai Zhao and Chunyu Kit. 2007a. Effective subsequence-based tagging for Chinese word segmentation (in Chinese). Journal of Chinese Information Processing, 21(5):8-13. Also in Maosong Sun & Qunxiu Chen (eds.), Frontiers of Content Computing: Research and Application, the Proceedings of the 9th Chinese National Conference on Computational Linguistics (CNCCL-2007, formerly JSCL-2007), pp. 45-51, Tsinghua University Press. Dalian, Aug. 6-8, 2007.

Chunyu Kit and Xiaoyue Liu. 2007. Mono-word termhood as rank difference in domain and background corpora. In International Conference: Keyness in Text, , pp 41-45. Pontignano, Siena, Italy, June 26-30 2007.
Chunyu Kit and Hai Zhao. 2007. Improving Chinese word segmentation with description length gain. In 2007 International Conference on Artificial Intelligence (ICAI'07), pp.846-851. Las Vegas, June 25-28, 2007.

Jing Li, Le Sun, Chunyu Kit and Jonathan Webster. 2007. A query-focused multi-document summarizer based on lexical chains. In DUC 2007, NIST, Rochester, NY, USA, 26-27 April 2007. http://www-nlpir.nist.gov/projects/duc/pubs.html.

2006

Zhiming Xu, Chunyu Kit and Jonathan J. Webster. 2006. Integration algorithm of English-Chinese word segmentation and alignment. In Proceedings of the 2006 International Conference on Machine Learning and Cybernetics (ICMLC 2006), pp.5105-4110. Available from IEEE Xplore here.
Zhiming Xu, Qiang Wang, Jonathan J. Webster, Chunyu Kit. 2006. An empirical study of the effectiveness of n-gram modeling in probabilistic Chinese word segmentation. International Journal of Computer Science and Network Security (IJCSNS), Vol. 6 No. 1 pp. 81-86. (Abstract)
Zhiming Xu, Jonathan J. Webster and Chunyu Kit. 2006. A new dictionary-based word alignment algorithm. Journal of Chinese Language and Computing 16(4):225-238. (Word File)
Chunyu Kit, Xiaoyue Liu, and Jonathan J. Webster. 2006. Abbreviation recognition with Maxent model. In Alexander Gelbukh (ed.), Computational Linguistics and Intelligent Text Processing: CICLing 2006, LNCS Vol. 3878, pp.117-120. Springer. PDF (263.1 KB)

2005

Chunyu Kit, and Xiaoyue Liu. 2005. An example-based Chinese word segmentation system for CWSB-2. SIGHAN-4, pp. 146-149. 14-15 Oct., Jeju Island.

Chunyu Kit, Xiaoyue Liu, King Kui Sin, and Jonathan J. Webster. 2005. Harvesting the bitexts of the laws of Hong Kong from the Web. In the 5th Workshop on Asian Language Resources (ALR-05), pp.71-78. 14 Oct., Jeju Island.

Chunyu Kit, and Xiaoyue Liu. 2005. Period disambiguation with Maxent model. In R. Dale, K-F Wong, J. Su & O Y Kwong (eds.), Natural Language Processing - IJCNLP 2005, LNAI 3651, pp.223-232. Springer. PDF (327.4 KB)

Chunyu Kit. 2005. Unsupervised lexical learning as inductive inference via compression. In J. W. Minett and W. S.Y. Wang (eds.), Language Acquisition, Change and Emergence, pp. 251-296. CityU of HK Press.

Haodi Feng, Kang Chen, Chunyu Kit, and Xiaotie Deng. 2005. Unsupervised segmentation of Chinese corpus using accessor variety. In K. Y. Su, J. Tsujii, J. H. Lee & O. Y. Kwong (eds.), Natural Language Processing - IJCNLP 2004, LNAI 3248, pp. 694-703. Springer. PDF (195.3 KB)

Qinan Hu, Haihua Pan, and Chunyu Kit. 2005. An example-based study on Chinese word segmentation using critical fragments. In K. Y. Su, J. Tsujii, J. H. Lee & O. Y. Kwong (eds.), Natural Language Processing - IJCNLP 2004, LNAI 3248, pp.714-722. Springer. PDF (359.2 KB)

2004

Chunyu Kit, Zhiming Xu, and Jonathan J. Webster. 2004. Integrating n-gram model and case-based learning for Chinese word segmentation. Journal of Chinese Language and Computing, 14(3):213-219.

Chunyu Kit, Jonathan J. Webster, King Kui Sin, Haihua Pan, and Heng Li. 2004. Clause alignment for bilingual HK legal texts: A lexical-based approach. International Journal of Corpus Linguistics 9(1):29-51.

2003

Heng Li, Jonathan J. Webster, Chunyu Kit, and Tianshun Yao. 2003. Transductive HMM based Chinese text chunking. IEEE NLP-KE2003, pp.257-262. Beijing.

Zhiming Xu, Chunyu Kit, and Jonathan J. Webster. 2003. An adaptive training algorithm for probabilistic language model and its application to Chinese word segmentation (in Chinese). In Maosong Sun and Qunxiu Chen (eds.), Language Computing and Content-based Text Processing, pp. 73-78. JSCL2003, Harbin, 8-12 Aug., 2003.

Chunyu Kit, Jonathan J. Webster, King Kui Sin, Haihua Pan, and Heng Li. 2003. Clause alignment for bilingual HK legal texts with available lexical resources. In Maosong Sun, Tianshun Yao, and Chunfa Yuan (eds.), Advances in Computation of Oriental Languages: 20th ICCPOL Proceedings, pp.286-292. Shenyang, 4-6 Aug., 2003.

Chunyu Kit, Zhiming Xu, and Jonathan J. Webster. 2003. Integrating n-gram model and case-based learning for Chinese word segmentation. In Qing Ma & Fei Xia (ed.), SIGHAN-2, pp.160-163. Sapporo, 11 July, 2003. (ACL-2003)

2002

Chunyu Kit. 2002. How does lexical acquisition begin? A cognitive perspective. Cognitive Science, 1(1):1-50. (.ps)

Chunyu Kit. 2002. Corpus tools for retrieving and deriving termhood evidence. In The 5th East Asia Forum of Terminology, pp.69-80. Haikou, China. Dec. 6, 2002.

Chunyu Kit, Haihua Pan and Jonathan J. Webster. 2002. Example-based machine translation: A new paradigm. In S.W. Chan (ed.), Translation and Information Technology, pp.57-78. Chinese U. of HK Press.

Chunyu Kit, Haihua Pan and Hongbiao Chen. 2002. Learning case-based knowledge for disambiguating Chinese word segmentation: A preliminary study. SIGHAN-1, pp. 33-39. 1 Sept., 2002. Taipei

Chunyu Kit. Naming in context: A case study of Chinese menu items in Hong Kong. First HKTerm 2002 - The Asian-Pacific Workshop on Terminology, 29-30 March, 2002, CityU of Hong Kong.

Before 2000

Chunyu Kit and Yorick Wilks. 1999. Unsupervised learning of word boundary with description length gain. In M. Osborne & E. T. K. Sang (eds.), CoNLL-99, pp.1-6. 12 June 12, Bergen, Norway.

Chunyu Kit 1998. Ba and bei as multi-valence prepositions in Chinese (.pdf). In Benjamin K. T'sou (ed.),Studia Linguistica Sinica, pp.497-522. Language Information Sciences Research Centre, City University of Hong Kong..

Chunyu Kit and Yorick Wilks. 1998. The Virtual Corpus approach to deriving n-gram statistics from large scale corpora.(.pdf) In C. N. Huang (ed.), Proceedings of 1998 International Conference on Chinese Information Processing Conference, pp.223-229. Nov. 18-20, Beijing.

Chunyu Kit. 1998. A goodness measure for phrase learning via compression with the MDL principle. In I. Kruijff-Korbayova(ed.), The ELLSSI-98 Student Session, Chapter 13, pp.175-187. Aug. 17-28, Saarbrueken.

Jonathan J. Webster and C. Kit. 1995. Computational analysis of Chinese and English texts with the functional semantic processor and the C-LFG parser. Literary and Linguistic Computing, 10(3):203-211. Oxford University Press.
Jonathan J. Webster and C. Kit. 1995. Automatic text analysis with the Functional Semantic Processor and the C-LFG parser. In Proceedings of the Third International Conference on the Practical Application of Prolog, pp.671-682, April 1995, Paris.
Chunyu Kit 1994. Automatic terminology extraction for thematic corpus based on subterm co-occurrence. In ROCLING\/-94, July, 1994, Taibei.
Chunyu Kit and J. Webster. 1992. Parsing Chinese pivotal constructions in an LFG approach. In Proceedings of 1992 International Conference on Computer Processing of Chinese and Oriental Languages, Dec. 15-19, 1992, Sand Key, Florida.
Chunyu Kit. 1992. Parsing Chinese ba and bei constructions - an LFG approach. In Proceedings of 3rd International Conference on Chinese Information Processing, October 12-16, 1992, Beijing.
Jonathan J. Webster and C. Kit. 1992. Tokenization as the initial phase in NLP. In COLING-92, Vol. IV, pp.1106-1110, July, 1992, Nantes, France.
Chunyu Kit, Yuan Liu and Nanyuan Liang. 1989. On methods of automatic Chinese word segmentation. Presented on 1st Conference on Computational Linguistics of China, June, 1988, Tsinghua University, Beijing. Revised version in Journal of Chinese Information Processing, 3(1):1-9. (in Chinese)

Poetry

My poetry page: in GB code and in Big5 code (not available yet).
My poems published in Olive Tree in GB, click here.
My peoms published in Olive Tree in Big5, click here.

Last modification: 22/05/2006, by Chunyu Kit