Jing-Shin Chang


2012

pdf bib
Effects of Combining Bilingual and Collocational Information on Translation of English and Chinese Verb-Noun Pairs
Yi-Hsuan Chuang | Chao-Lin Liu | Jing-Shin Chang
International Journal of Computational Linguistics & Chinese Language Processing, Volume 17, Number 3, September 2012

2011

pdf bib
Translating Common English and Chinese Verb-Noun Pairs in Technical Documents with Collocational and Bilingual Information
Yi-Hsuan Chuang | Chao-Lin Liu | Jing-Shin Chang
Proceedings of the 25th Pacific Asia Conference on Language, Information and Computation

2010

pdf bib
An Automatic Query Augmentation Model for Answering Well-Defined Questions in Top-1 Search Result
Jing-Shin Chang | Shu-Fan Shih
Proceedings of the 22nd Conference on Computational Linguistics and Speech Processing (ROCLING 2010)

2009

pdf bib
An EM Algorithm for Context-Based Searching and Disambiguation with Application to Synonym Term Alignment
Jing-Shin Chang | Shih-Jay Chiou
Proceedings of the 23rd Pacific Asia Conference on Language, Information and Computation, Volume 2

pdf bib
Improving Translation Fluency with Search-Based Decoding and a Monolingual Statistical Machine Translation Model for Automatic Post-Editing
Jing-Shin Chang | Sheng-Sian Lin
Proceedings of the 21st Conference on Computational Linguistics and Speech Processing

pdf bib
Hierarchical Web Document Classification Based on Hierarchically Trained Domain Specific Words
Jing-Shin Chang
ROCLING 2009 Poster Papers

2007

pdf bib
A Chinese-to-Chinese statistical machine translation model for mining synonymous simplified-traditional Chinese terms
Jing-Shin Chang | Chun-Kai Kung
Proceedings of Machine Translation Summit XI: Papers

2006

pdf bib
Mining Atomic Chinese Abbreviation Pairs: A Probabilistic Model for Single Character Word Recovery
Jing-Shin Chang | Wei-Lun Teng
Proceedings of the Fifth SIGHAN Workshop on Chinese Language Processing

2005

pdf bib
Domain Specific Word Extraction from Hierarchical Web Documents: A First Step Toward Building Lexicon Trees from Web Corpora
Jing-Shin Chang
Proceedings of the Fourth SIGHAN Workshop on Chinese Language Processing

2004

pdf bib
A Preliminary Study on Probabilistic Models for Chinese Abbreviations
Jing-Shin Chang | Yu-Tso Lai
Proceedings of the Third SIGHAN Workshop on Chinese Language Processing

1999

pdf bib
A customizable, self-learning parameterized MT system: the next generation
Keh-Yih Su | Jing-Shin Chang
Proceedings of Machine Translation Summit VII

In this paper, the major problems of the current machine translation systems are first outlined. A new direction, highlighting the system capability to be customizable and self-learnable, is then proposed for attacking the described problems, which are mainly resulted from the very complicated characteristics of natural languages. The proposed solution adopts an unsupervised two-way training mechanism and a parameterized architecture to acquire the required statistical knowledge, such that the system can be easily adapted to different domains and various preferences of individual users.

1997

pdf bib
A Multivariate Gaussian Mixture Model for Automatic Compound Word Extraction
Jing-Shin Chang | Keh-Yih Su
Proceedings of the 10th Research on Computational Linguistics International Conference

pdf bib
Computational Tools and Resources for Linguistic Studies
Yu-Ling Una Hsu | Jing-Shin Chang | Keh-Yih Su
International Journal of Computational Linguistics & Chinese Language Processing, Volume 2, Number 1, February 1997: Special Issue on Computational Resources for Research in Chinese Linguistics

pdf bib
An Unsupervised Iterative Method for Chinese New Lexicon Extraction
Jing-Shin Chang | Keh-Yih Su
International Journal of Computational Linguistics & Chinese Language Processing, Volume 2, Number 2, August 1997

pdf bib
Corpus-Based Statistics-Oriented (CBSO) Machine Translation Researches in Taiwan
Jing-Shin Chang | Keh-Yih Su
Proceedings of Machine Translation Summit VI: Papers

A brief introduction to the MT research projects in Taiwan is given in this paper. Special attention is given to the more and more popular corpus-based statistics-oriented (CBSO) approaches in MT researches. In particular, the parameterized two-way training philosophy in designing the second generation BehaviorTran, which is the first and the largest operational system in this area, is introduced in this paper.

1996

pdf bib
An Overview of Corpus-Based Statistics-Oriented (CBSO) Techniques for Natural Language Processing
Keh-Yih Su | Tung-Hui Chiang | Jing-Shin Chang
International Journal of Computational Linguistics & Chinese Language Processing, Volume 1, Number 1, August 1996

1995

pdf bib
A Corpus-based Two-Way Design for Parameterized MT Systems: Rationale, Architecture and Training Issues
Keh-Yih Su | Jing-Shin Chang | Yu-Ling Una Hsu
Proceedings of the Sixth Conference on Theoretical and Methodological Issues in Machine Translation of Natural Languages

pdf bib
Automatic Construction of a Chinese Electronic Dictionary
Jing-Shin Chang | Yi-Chung Lin | Keh-Yih Su
Third Workshop on Very Large Corpora

1994

pdf bib
A Corpus-based Approach to Automatic Compound Extraction
Keh-Yih Su | Ming-Wen Wu | Jing-Shin Chang
32nd Annual Meeting of the Association for Computational Linguistics

pdf bib
An Automatic Treebank Conversion Algorithm for Corpus Sharing
Jong-Nae Wang | Jing-Shin Chang | Keh-Yih Su
32nd Annual Meeting of the Association for Computational Linguistics

1993

pdf bib
A Corpus-Based Statistics-Oriented Transfer and Generation Model for Machine Translation
Jing-Shin Chang | Keh-Yih Su
Proceedings of the Fifth Conference on Theoretical and Methodological Issues in Machine Translation of Natural Languages

1992

pdf bib
Statistical Models for Word Segmentation And Unknown Word Resolution
Tung-Hui Chiang | Jing-Shin Chang | Ming-Yu Lin | Keh-Yih Su
Proceedings of Rocling V Computational Linguistics Conference V

pdf bib
A New Quantitative Quality Measure for Machine Translation Systems
Keh-Yih Su | Ming-Wen Wu | Jing-Shin Chang
COLING 1992 Volume 2: The 14th International Conference on Computational Linguistics

pdf bib
GPSM: A Generalized Probabilistic Semantic Model for Ambiguity Resolution
Jing-Shin Chang | Yih-Fen Luo | Keh-Yih Su
30th Annual Meeting of the Association for Computational Linguistics

pdf bib
Why corpus-based statistics-oriented machine translation
Keh-Yih Su | Jing-Shin Chang
Proceedings of the Fourth Conference on Theoretical and Methodological Issues in Machine Translation of Natural Languages

1991

pdf bib
ArchTran: A Corpus-based Statistics-oriented English-Chinese Machine Translation System
Shu-Chuan Chen | Jing-Shin Chang | Jong-Nae Wang | and Keh-Yih Su
Proceedings of Machine Translation Summit III: Papers

The ArchTran English-Chinese Machine Translation System is among the first commercialized English-Chinese machine translation systems in the world. A prototype system was released in 1989 and currently serves as the kernel of a value-added network-based translation service. The main design features of the ArchTran system are the adoption of a mixed (bottom-up parsing with top-down filtering) parsing strategy, a scored parsing mechanism, and the corpus-based, statistics-oriented paradigm for linguistic knowledge acquisition. Under this framework, research directions are toward designing systematic and automatic methods for acquiring language model parameters, and toward using preference measure with uniform probabilistic score function for ambiguity resolution. In this paper, the underlying probabilistic models of the ArchTran designing philosophy will be presented.

1990

pdf bib
The Semantic Score Approach to the Disambiguation of PP Attachment Problem
Chao-Lin Liu | Jing-Shin Chang | Keh-Yih Su
Proceedings of Rocling III Computational Linguistics Conference III

1989

pdf bib
A Sequential Truncation Parsing Algorithm Based on the Score Function
Keh-Yih Su | Jong-Nae Wang | Mei-Hui Su | Jing-Shin Chang
Proceedings of the First International Workshop on Parsing Technologies

In a natural language processing system, a large amount of ambiguity and a large branching factor are hindering factors in obtaining the desired analysis for a given sentence in a short time. In this paper, we are proposing a sequential truncation parsing algorithm to reduce the searching space and thus lowering the parsing time. The algorithm is based on a score function which takes the advantages of probabilistic characteristics of syntactic information in the sentences. A preliminary test on this algorithm was conducted with a special version of our machine translation system, the ARCHTRAN, and an encouraging result was observed.

1988

pdf bib
Incremental Environment For Scored Machine Translation Systems
Jing-Shin Chang | Keh-Yih Su
Proceedings of Rocling I Computational Linguistics Conference I

pdf bib
Semantic and Syntactic Aspects of Score Function
Keh-Yih Su | Jing-Shin Chang
Coling Budapest 1988 Volume 2: International Conference on Computational Linguistics