Divider
  Speech Technology and Research Laboratory
  People
  Current Research Activities
  Past Research Activities
  Publications
  Career Opportunities
  Seminars
  Technologies for License
  In the News
  Contact Us
  STAR Search
  Information and Computing Sciences Division
SpacerAbout UsDividerR and D DivisionsDividerCareersDividerNewsroomDividerContact UsDividerSRI HomeSpacer

Spacer
         
  SRI Logo

Necip Fazil AYAN

Research Engineer

Contact Information

Speech Technology & Research Laboratory
SRI International
333 Ravenswood Avenue
Menlo Park, CA 94025 (USA)
Tel: (650) 859-5653
Fax: (650) 859-5984
Necip Fazil Ayan

Research Interests

  • Natural language processing, particularly on machine translation, word/phrase alignment, and paraphrasing/summarization
  • Machine learning and its application to natural language processing problems
  • Evidence combination
  • Computational linguistics, focusing on incorporation of linguistic knowledge to statistical models

Education

  • Ph.D., Computer Science, University of Maryland, College Park, 2005.
  • M.S., Computer Science, University of Maryland, College Park, 2003.
  • M.S., Computer Engineering and Information Science, Bilkent University, Turkey, 1999.
  • B.S., Computer Engineering and Information Science, Bilkent University, Turkey, 1997.

Projects

Publications

  • Jing Zheng, Wen Wang, and Necip Fazil Ayan. Development of SRI's Translation Systems for Broadcast News and Broadcast Conversations. To appear in Proceedings of Interspeech'08, Brisbane, Australia, September 22-26, 2008.
  • Necip Fazil Ayan, Jing Zheng, and Wen Wang. Improving Alignments for Better Confusion Networks for Combining Machine Translation Systems. To appear in Proceedings of the 22nd International Conference on Computational Linguistics (COLING'08), Manchester, UK, August 18-22, 2008.
  • Nitin Madnani, Necip Fazil Ayan, Philip Resnik, and Bonnie J. Dorr. Using Paraphrases for Parameter Tuning in Statistical Machine Translation. In Proceedings of the 2nd Workshop on Statistical Machine Translation (WMT'07) at ACL'07, Prague, Czech Republic, June 23, 2007.
  • Nitin Madnani, Rebecca Passonneau, Necip Fazil Ayan, Bonnie J. Dorr, Judith Klavans, D. O'Leary, John Conroy, and Judith Schlesinger. Variability in Sentence Ordering across Multiple Subjects: An Argument for Multiple References in Evaluation. In Proceedings of 11th European Workshop on Natural Language Generation (ENLG'07), Dagstuhl, Germany, June 17-20, 2007.
  • Nitin Madnani, David Zajic, Bonnie J. Dorr, Necip Fazil Ayan, and Jimmy Lin. Employing Multiple Alternative Sentence Compressions for Automatic Text Summarization. In Proceedings of the Document Understanding Conference (DUC'07) at HLT-NAACL'07, Rochester, New York, April 26, 2007.
  • Antti-Veikko Rosti, Necip Fazil Ayan, Bing Xiang, Spyros Matsoukas, Richard Schwartz, and Bonnie J. Dorr. Combining Translations from Multiple Machine Translation Systems. In Proceedings of the Conference on Human Language Technology and North American Chapter of the Association for Computational Linguistics Annual Meeting (HLT-NAACL'2007), pages 228-235, Rochester, NY, April 22-27, 2007. *** Best paper award ***
  • Necip Fazil Ayan, and Bonnie J. Dorr. Going Beyond AER: An Extensive Analysis of Word Alignments and Their Impact on MT. In Proceedings of the Joint Conference of the International Committee on Computational Linguistics and the Association for Computational Linguistics (COLING-ACL'2006) , pages 9-16, Sydney, Australia, July 17-21, 2006.
  • Necip Fazil Ayan, and Bonnie J. Dorr. A Maximum Entropy Approach to Combining Word Alignments. In Proceedings of the Conference on Human Language Technology and North American Chapter of the Association for Computational Linguistics Annual Meeting (HLT-NAACL'2006), pages 96-103, New York, NY, June 5-7, 2006.
  • Necip Fazil Ayan. Combining Linguistic and Machine Learning Techniques for Word Alignment Improvement. PhD Thesis, University of Maryland, College Park, November 2005.
  • Necip Fazil Ayan, Bonnie J. Dorr, and Christof Monz. Alignment Link Projection Using Transformation-Based Learning. In Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing (HLT-EMNLP'2005), pages 185-192, Vancouver, BC, Canada, October 6-8, 2005. [Bibtex]
  • Necip Fazil Ayan, Bonnie J. Dorr, and Christof Monz. NeurAlign: Combining Word Alignments Using Neural Networks. In Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing (HLT-EMNLP'2005), pages 65-72, Vancouver, BC, Canada, October 6-8, 2005. [Bibtex]
  • Necip Fazil Ayan, Bonnie J. Dorr, and Nizar Habash. Multi-Align: Combining Linguistic and Statistical Techniques to Improve Alignments for Adaptable MT. In Proceedings of the 6th Conference of the Association for Machine Translation in the Americas (AMTA'2004), pages 17-26, Georgetown University, Washington DC, September 29-October 2, 2004.
  • Bonnie J. Dorr, Necip Fazil Ayan, Nizar Habash, Nitin Madnani, and Rebecca Hwa. Rapid Porting of DUSTer to Hindi. ACM Transactions on Asian Language Information Processing (TALIP), 2:2, pages 118-123, 2003.
  • Necip Fazil Ayan, Bonnie Dorr, and Okan Kolak. Domain Tuning of Bilingual Lexicons for MT. In Proceedings of the Evaluation Workshop at the MT Summit IX, pages 3-11, New Orleans, Louisiana, September 23-27, 2003.
  • Necip Fazil Ayan, and Bonnie J. Dorr. Generating A Parsing Lexicon from an LCS-based Lexicon. In Proceedings of the LREC'2002 Workshop on Linguistic Knowledge Acquisition and Representation, pages 43-52, Las Palmas, Canary Islands, Spain, June 2002.
  • Necip Fazil Ayan, Wen-Syan Li, and Okan Kolak. Automating Extraction of Logical Domains in a Web Site. Data Knowledge and Engineering, 43:2, pages 179-205, 2002.
  • Wen-Syan Li, Necip Fazil Ayan, Okan Kolak, Quoc Vu, Hajime Takano, and Hisashi Shimamura. Constructing Multi-granular and Topic-focused Web Site Maps. In Proceedings of the 10th World Wide Web Conference (WWW'2001), pages 343-354, Hong Kong, China, May 2001.
  • Necip Fazil Ayan. Updating Large Itemsets with Early Pruning. M.Sc. Thesis, Bilkent University, Ankara, Turkey, July 1999.
  • Necip Fazil Ayan, Abdullah Uz Tansel, and Erol Arkun. An Efficient Algorithm to Update Large Itemsets with Early Pruning. In Proceedings of ACM SIGKDD International Conference on Knowledge Discovery in Data and Data Mining (SIGKDD'99), pages 287-291, San Diego, California, August 1999.
  • Necip Fazil Ayan. Using Information Gain as Feature Weight. In Proceedings of the 8th Turkish Symposium on Artificial Intelligence and Neural Networks (TAINN'99), Istanbul, Turkey, June 1999.
  • Abdullah Uz Tansel, and Necip Fazil Ayan. Discovery of Association Rules in Temporal Databases. In Proceedings of the 4th International Conference on Knowledge Discovery and Data Mining (KDD'1998) Distributed Data Mining Workshop, New York, NY, August 1998.

 

About Us  Vertical divider  R&D Divisions  Divider  Careers  Divider  Newsroom  Divider  Contact Us
©2011 SRI International, 333 Ravenswood Avenue, Menlo Park, CA 94025-3493
SRI International is an independent, nonprofit corporation. Privacy policy

Last modified Dec 16, 2010