Course ti<x>tle：機器翻譯實作 (Machine Translation Lab) 教室：資電 326
<br>Course number：ISA 663500
<br>Instructor： 張俊盛
<br>The course consists of a set of small exercises on machine translation ba<x>sed on statistical approach. 
<br>The purpose is to give students opportunity to get hand on experience by working with problems and 
<br>data available from the NIST Open Machine Translation (MT) evaluation series (1). The course will cover 
<br>the fundaments of machine translation, open-source tools for developing an MT systems and hands-
<br>on sessions. The hands-on session will start with explanation of background, experimental data, and 
<br>snippets of code. The students are required to do the assignment in class. The instructor and teaching 
<br>assistants will be on hand to help students. The list of topics planned for the Fall, 2007 is as follows. 
<br>The Official programming language is Python.
<br>
<br>Topics
<br>1.	Introduction
<br>2.	Machine translation and statistical machine translation
<br>3.	The NIST Open Machine Translation (MT) evaluation series 
<br>4.	Subsentential alignment 
<br>5.	Word alignment
<br>6.	Phrase alignment using parallel corpus
<br>7.	Phrase alignment using non-parallel corpus
<br>8.	Class ba<x>sed word and phrase alignment
<br>9.	Word and phrase ba<x>sed decoder
<br>10.	Syntax directed SMT
<br>11.	Parsing and bilingual parsing
<br>12.	Integration of Word Sense Disambiguation into MT
<br>13.	Web as corpus (monolingual or bilingual)
<br>14.	Web Mining of bilingual texts (paragraphs, phrases, word translations)
<br>15.	Machine translation evaluation
<br>16.	System integration
<br>
<br>
<br>Reading
<br>
<br>1.	Machine Translation Workbook, by Kevin Knight. 
<br>www.isi.edu/~knight/ and www.isi.edu/natural-language/mt/wkbk.rtf
<br>2.	What is new in Statistical Machine Translation by Kevin Knight. 
<br>l2r.cs.uiuc.edu/~danr/Teaching/CS598-05/Lectures/knight.ppt.
<br>3.	Lecture Notes of the Second Machine Translation Marathon, Berlin, Germany, May 12-20, 2008.
<br>4.	Related li<x>nk of the event:
<br>schedule: http://euromatrix.net/events/second-machine-translation-marathon/
<br>wiki: http://www.statmt.org/mtm2/?n=Main.HomePage
<br>
<br>References:
<br>5.	NIST Open Machine Translation Home, http://www.nist.gov/speech/tests/mt/.
<br>6.	SPEECH and LANGUAGE PROCESSING: An Introduction to Natural Language Processing, 
<br>Computational Linguistics , and Speech Recognition, Jurafsky and Martin, Ch. 25, MT, 
<br>http://www.cs.colorado.edu/~martin/slp2.html#Chapter24
<br>7.	Using collocations from comparable corpora to find translation equivalents, S Sharoff, B Babych, A 
<br>Hartley, Proceedings of the International Conference on Language, 2006.
<br>8.	ASSIST: Automated semantic assistance for translators, S Sharoff, B Babych, P Rayson, O Mudraya, S 
<br>Piao, Proceedings of EACL, 2006.
<br>9.	A hierarchical phrase-ba<x>sed model for statistical machine translation, D Chiang - Proceedings of 
<br>the 43rd Annual Meeting on Association for Computational Linguistics, 2005.
<br>10.	Fast and optimal decoding for machine translation, U Germann, M Jahr, K Knight, D Marcu, K 
<br>Yamada - Artificial Intelligence, 2004.
<br>11.	The alignment template approach to statistical machine translation, FJ Och, H Ney, Computational 
<br>Linguistics, 2004, MIT Press.
<br>12.	Integer programming decoder for machine translation, K Knight, K Yamada - US Patent 7,177,792, 
<br>2007 - Google Patents.
<br>13.	Clause Restructuring for Statistical Machine Translation - M Collins, P Koehn, I Kucerova – Annual 
<br>Meeting of the ACL, 2005.
<br>14.	Novel reordering approaches in phrase-ba<x>sed statistical machine translation - S Kanthak, D Vilar, E 
<br>Matusov, R Zens, H Ney – Workshop on Building and Using Parallel Texts: Data-Driven Machine 
<br>Translation and Beyond, 2005.
<br>15.	Integration of POS tag-ba<x>sed source reordering into SMT decoding by an extended search graph, 
<br>JM Crego, JB Marino – Conference of the Association for Machine Translation in the Americas, 2006.
<br>16.	Local search with very large-scale neighborhoods for optimal permutations in machine translation, 
<br>J Eisner, RW Tromble - Proceedings of the Human Language Technology (HLT), 2006.
<br>17.	Filtering multilingual Web content using fuzzy logic and self-organizing maps - R Chau, CH Yeh - 
<br>Neural Computing & Applications, 2004 - Springer
<br>18.	Using bilingual comparable corpora and semi-supervised clustering for topic tracking. F 
<br>Fukumoto, Y Suzuki - Proceedings of the COLING/ACL, 2006.
<br>19.	Large Language Models in Machine Translation - T Brants, A Popat, P Xu, F Och, J Dean - 
<br>Proceedings of the 2007 Joint Conference on Empirical Natural Language Processing, 2007.
<br>20.	Monolingual machine translation for paraphrase generation - C Quirk, C Brockett, W Dolan - 
<br>Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing, 2004.
<br>21.	Translation Exercise Assistant: Automated Generation of Translation Exercises for Native-Arabic 
<br>speaker, J Burstein, D Marcu - Proceedings of HLT/EMNLP on Interactive Demonstrations, 2005.
<br>22.	SPMT: Statistical Machine Translation with Syntactified Target Language Phrases, D Marcu, W Wang, 
<br>A Echihabi, K Knight - Proceedings of EMNLP, Sydney, Australia, 2006.
<br>23.	Improving Machine Translation Performance by Exploiting Non-Parallel Corpora - DS Munteanu, D 
<br>Marcu - Computational Linguistics, 2005
<br>24.	Improved statistical machine translation using paraphrases - C Callison-Burch, P Koehn, M 
<br>Osborne - Proceedings of the main conference on Human Language Technology, 2006
<br>25.	Scaling phrase-ba<x>sed statistical machine translation to larger corpora and longer phrases - C 
<br>Callison-Burch, C Bannard, J Schroeder - Proceedings of the 43rd Annual Meeting on Association for 
<br>Computational Linguistics, 2005
<br>26.	Named entity translation, K Knight, Y Al-Onaizan - US Patent 7,249,013, 2007 - patentstorm.us
<br>27.	Machine Reading - O Etzioni, M Banko, MJ Cafarella - 2007 AAAI Spring Symposium on Machine 
<br>Reading, 2007.
<br>28.	A Comparative Study on Compositional Translation Estimation using a Domain/Topic-Specific 
<br>Corpus collected from the Web - M Tonoike, et al. Proc. 2nd International Workshop on Web as Corpus, 
<br>2006.
<br>29.	Mining translations of OOV terms from the web through cross-lingual query expansion - Y Zhang, 
<br>F Huang, S Vogel - Proceedings of the 28th annual international ACM SIGIR, 2005
<br>30.	The Wikipedia xm<x>l corpus - L Denoyer, P Gallinari - ACM SIGIR Forum, 2006.
<br>
<br>
<br>Available Software 
<br>
<br>1.	Giza++
<br>2.	Pharaoh 
<br>3.	Moses
<br>
<br>(Robert C. Moore, Microsoft Research)
<br>
<br>1.	Bilingual Sentence Aligner When people translate documents from one language to another, not all 
<br>sentences are translated one-for-one. Perl code implementation
<br>2.	Context-Free Parsing Algorithms Implementations of several parsing algorithms.
<br>3.	Unification Grammar Sentence Realization Algorithms Prolog implementations of two versions of 
<br>the unfication grammar sentence realization algorithm.
<br>
<br>五、教學進度(Syllabus)
<br>
<br>六、成績考核(Evaluation)
<br>
<br>以小考、上機作業及進度報告為主。
<br>
<br>七、可連結之網頁位址
<br>
<br>張俊盛老師的網頁：http://nlp.cs.nthu.edu.tw/nlplab/teacher.htm
<br>張智星老師的網頁：http://www.cs.nthu.edu.tw/~jang
<br>