|
Nizar Y. Habash http://www.NizarHabash.com * Nizar@NizarHabash.com EDUCATION
Ph.D. Computer Science, 2003. University of Maryland College Park. Dissertation: “Generation-Heavy Hybrid Machine Translation” (URL) M.S. Computer Science, 2000. University of Maryland College Park. B.S. Computer Engineering, 1997, summa cum laude. Old Dominion University. B.A. Linguistics and Languages, 1997, summa cum laude. Old Dominion University. RESEARCH EXPERIENCE
Columbia University July/2005 - present Center for Computational Learning Systems Associate Research Scientist — Co-founded the Columbia Arabic Dialect Modeling (CADIM) group. (http://www.ccls.columbia.edu/cadim/) — Senior member in an NSF funded Johns Hopkins Summer Workshop on Arabic Dialect Parsing — Member of the DARPA-funded "Novel Information Gathering and Harvesting Techniques in a Global Autonomous Environment (NIGHTINGALE)" project working on Arabic modeling and Machine Translation. — Collaborated with Textwise on their Arabic CINDOR (Conceptual INterlingua DOcument Retrieval) Project. — Collaborated with other Columbia University researcher on a KDD project on email and newsgroup summarization.
Columbia University July/2004 – July/2005 Post-doctoral Researcher · Worked in a NSF ITR on Arabic Dialect Modeling for Speech and Natural Language (PIs Kathy McKeown and Owen Rambow).
University of Maryland College Park July/2003 – July/2004 Post-doctoral Researcher · An active member of the six-site project, Interlingual Annotation for Multilingual Text Corpora (IAMTC). · Managed the Divergence Unraveling for Statistical Translation (DUSTer) project. · Managed the Generation-heavy Hybrid Machine Translation (GHMT) effort at University of Maryland College Park. · Worked with a graduate student to extend the GHMT approach to handle English headline generation from foreign text (in collaboration with Bonnie Dorr).
University of Maryland College Park 1998-2003 Graduate Research Assistant — Member of the English language generation group working as a part of a large project for Chinese-English machine translation. — Explored methods for large scale language-independent natural language generation. — Wrote rules to transform Lexical Conceptual Structure (LCS) interlingual representation into Abstract Meaning Representation (AMR) to input into Nitrogen (a natural language generation system). — Presented on behalf of the generation group in several Interim Progress Reports for Chinese-English machine translation project. — Developed the Multi-faceted Tree Viewer: a zoomable user interface for viewing highly ambiguous sentence analyses. — Designed and implemented a web-based survey for evaluating the accuracy and fluency of the Chinese-English MT system. — Designed and implemented a web-based interface for browsing, searching, and editing the Lexical Conceptual Structure Lexicon for English, Spanish and Chinese. — Spearheaded an effort in the CLIP lab to define a unified interface standard across all its diverse projects to encourage higher levels of cooperation between the researchers. — Assisted with research on Arabic as part of DUSTER (Divergence Unraveling for Statistical Translation)
Old Dominion University Spring/Summer 1996 Undergraduate Research Assistant Member of the ModSAF research team at Old Dominion University's computer science department. Analyzed and tested modules of the 800K line program. Created a general documentation reference for the different modules of the ModSAF system
Old Dominion University Fall 1994 Undergraduate Research Project: LinguisTree Received an undergraduate research award to design and implement LinguisTree, a program to help teach university-level American students about English grammar.
Computer Skills — Hardware: Strong background in digital design and microcontrollers. — Software: Extensive software experience under Windows, Dos and Unix and internet web design. — Resources: WordNet, CMU Toolkit, LCS Lexicons, Nitrogen/Halogen, Yamcha machine learning system, Ripper, Buckwalter Arabic analyzer, AT&T FSM toolkit, SRILM toolkit, Lextools. — Languages: High fluency: Java, Perl, Lisp, C, Visual Basic, (D)HTML, JavaScript, oxyL. Comfortable fluency: Pascal, Basic, C++, Prolog, MatLab, SubL, Php, SQL, Flash
WORK EXPERIENCE
Nuun Labs, Inc. 1999-2000 Chief Technical Officer Designed and implemented the company's main products: NuunPad, NuunBuilder, NuunConvert, NuunForms, and NuunEncoding. Constructed the initial web site for Nuun technology. Provided technical support to most of NuunLabs clients. Led presentations on Nuun in an academic conference and for possible investors.
CYCORP, Inc. Summer 1998 Intern / Ontological Engineer The Natural Language Processing Group Designed and implemented PreGen (Preprocessor Generator) and PIL (Preprocessing Instruction Language). Extensive work with the CYC knowledge base including writing rules and queries for CYC.
TEACHING EXPERIENCE
Lecturer Co-instructor with Professor Bonnie Dorr. Designed and Presented half of the class lectures to a class of 35 students Designed assignments and projects and graded exams. CMSC 723/LING 645: Introduction to Computational Linguistics University of Maryland College Park , Spring 2004 URL
Diab, Mona and Nizar Habash. Arabic Dialect Processing. A three-hour tutorial (15 attendees) at the Conference of the North American Association for Computational Linguistics (NAACL’07), 2007.
Diab, Mona and Nizar Habash. Arabic Dialect Processing. A three-hour tutorial (8 attendees) at the Association for Machine Translation in the Americas (AMTA’06), Boston, MA, 2006.
Habash, Nizar. Introduction to Arabic Natural Language Processing. A three-hour tutorial (~35 attendees). Johns Hopkins University Summer School on Human Language Technology, Baltimore, 2006.
Habash, Nizar. Introduction to Arabic Natural Language Processing. A three-hour tutorial (20 attendees) at the International Conference on Language Resources and Evaluation, Genoa, Italy, 2006.
Habash, Nizar. Introduction to Arabic Natural Language Processing. A three-hour tutorial (40 attendees) at BBN Technologies, Boston, Massachusetts, August 29, 2005.
Habash, Nizar. Introduction to Arabic Natural Language Processing. A three-hour tutorial (20 attendees) at the National Cryptologic Muesum. August 2005.
Habash, Nizar. Introduction to Arabic Natural Language Processing. Three one-hour lecture series (50 attendees on average). Johns Hopkins University Summer Workshop, Baltimore, Maryland, July 2005.
Habash, Nizar. Introduction to Arabic Natural Language Processing: Words (1 hour reduced lecture as part of a session on Parsing Colloquial Arabic). Johns Hopkins University Summer School on Human Language Technology, Baltimore July 6, 2005.
Habash, Nizar. Introduction to Arabic Natural Language Processing. A three-hour tutorial (35 attendees) at the Association for Computational Linguistics Conference (ACL’05), Ann Arbor, Michigan, June 25, 2005.
Habash, Nizar. Introduction to Arabic Natural Language Processing. A three-hour tutorial (17 attendees) at the Association for Machine Translation in the Americas conference (AMTA’04), Georgetown University, Washington DC, September 28, 2004.
Guest Lecturer Machine Translation: Challenges, Approaches and Evaluation, CS 4705: Introduction to Natural Language Processing, Columbia University, Fall 2006
Machine Translation: Challenges, Approaches and Evaluation, CS 4705: Introduction to Natural Language Processing, Columbia University, Fall 2005
Machine Translation: Challenges, Approaches and Evaluation, CS 4705: Introduction to Natural Language Processing, Columbia University, Fall 2004 (Syllabus) (Slides)
Machine Translation: Challenges and Approaches, CMSC 421: Introduction to Artificial Intelligence, University of Maryland College Park, Fall 2003 (Syllabus) (Slides)
Generation Heavy Hybrid Machine Translation, CMSC 723/LING 645: Introduction to Computational Linguistics, University of Maryland College Park, Spring 2003
Computers and Writing Systems, HONR 279I: History of the Alphabets, 2000 BCE to 2000 CE: Languages and Their Scripts, University of Maryland College Park, Spring 2003
Natural Language Generation, CMSC 828: Advanced Natural Language Processing: Theory and Practice, University of Maryland College Park, Spring 2002
Teaching Assistant GVPT 309X: Topics in International Relations: Conflict Resolution - The Israeli Palestinian Experiment, University of Maryland College Park, Summer 2001
Grader for CMSC 150: Introduction to Discrete Mathematics, University of Maryland College Park, Fall 1997
Grader for CS390: Theoretical Computer Science, Old Dominion University, Spring 1997 Grader for CS311: Navigating the Internet, Old Dominion University, Spring 1997 Data consultant on Palestinian Arabic in ENGL 495: Linguistic Field Methods, Old Dominion University, Summer 1993
Teaching Material Design and Implementation
Created an introductory course to machine translation as a part of senior project in linguistics. Included class notes, an annotated bibliography, homework problems, exams, projects and a course pack for the class. Old Dominion University, Fall 1996
Created an Arabic exercise book for English Speakers to accompany the textbook for Arabic 101. Old Dominion University, Fall 1993
Student Advising/Supervision Over the last three years, I have been heavily involved in the advising of two PhD students at the University of Maryland, one PhD student at Copenhagen Business School (Denmark), one PhD student from Cairo University, and one Masters Student at Ben-Gurion University (Israel). Additionally, I supervised the work of ten students working on six different projects in University of Maryland and Columbia University. HONORS AND RECOGNITIONAwards — Graduate Student Service Award, University of Maryland College Park, 2003 — The Phi Kappa Phi Award of Excellence, Phi Kappa Phi, 1997/1998 — The College of Engineering and Technology Outstanding Scholar Award, Old Dominion University, 1997 — The Faculty Award in Computer Engineering, College of Engineering and Technology, Old Dominion University, 1997 — The Outstanding Individualized Study Student Award, College of Arts and Letters, Old Dominion University, 1997 — The Award of Academic Excellence, Academic Honors Program Old Dominion University,1997 — The Meghan O'Connor Award for Academic Achievement and Community Service, Academic Honors Program, Old Dominion University, 1997 — A nominee for USA Today's Best and Brightest, Old Dominion University, 1996 — Undergraduate Research Award, Academic Honors Program, Old Dominion University, 1994 — First Place in the 1993 Women Studies Undergraduate Essay Contest, Old Dominion University, 1993 — Dean's List, Old Dominion University, 1992-1997
Fellowships, Scholarships — AMTA Student Travel Grant, The Association of Machine Translation in the Americas, 2002 — The Samuel N. Alexander Fellowship, Association for Computing Machinery, Washington D.C. Chapter, 2001 — Kovner Scholarship, Old Dominion University, 1996/97 — Charles H. Eure Memorial Scholarship, Old Dominion University, 1996/97 — Cranmer/Skinner Scholarship, Old Dominion University, 1996/97 — Claire Nesson Scholarship, Old Dominion University, 1995/1996 — Stuart Russell Scholarship, Old Dominion University, 1994/95 — Cranmer/Skinner Scholarship, Old Dominion University, 1993/94 — Dual Degree Program Award, Old Dominion University, 1993 — Academic Honors Program Scholarship, Old Dominion University, 1992-1997 — UNESCO Fellowship, United Nations Educational, Scientific and Cultural Organization, Fall 1996, Spring 1995, Spring 1994,Summer 1993, Spring 1993
Honor Societies — Member of Phi Kappa Phi National Honor Society — Member of Tau Beta Pi (Computer Engineering Honor Society) — Member of Eta Kappa Nu (Electrical Engineering Honor Society) — Member of Golden Key National Honor Society — Member of Pi Delta Phi (French Honor Society)
PUBLICATIONS AND PRESENTATIONS PublicationsIn Preparation
Habash, Nizar and Fatiha Sadat. Arabic Preprocessing Schemes and Combinations for Statistical Machine Translation, in preparation.
Habash, Nizar, Bonnie Dorr and Christof Monz. Symbolic to Statistical Hybrid Machine Translation: The Case of Generation-Heavy MT. in preparation. 2007Habash, Nizar. Syntactic Preprocessing for Statistical Machine Translation, In Proceedings of the Machine Translation Summit (MT-Summit), Copenhagen, Denmark, 2007. Diab, Mona, Mahmoud Ghoneim and Nizar Habash. Arabic Diacritization in the Context of Statistical Machine Translation, In Proceedings of the Machine Translation Summit (MT-Summit), Copenhagen, Denmark, 2007. Kirchhoff, Katrin, Owen Rambow, Nizar Habash, Mona Diab. Semi-Automatic Error Analysis for Large-Scale Statistical Machine Translation Systems, In Proceedings of the Machine Translation Summit (MT-Summit), Copenhagen, Denmark, 2007. Habash, Nizar, Ryan Gabbard, Owen Rambow, Seth Kulick and Mitch Marcus. Determining Case in Arabic: Learning Complex Linguistic Behavior Requires Complex Linguistic Features, In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), Prague, Czech Republic, 2007. Habash, Nizar and Owen Rambow. Arabic Diacritization through Full Morphological Tagging, In Proceedings of the North American chapter of the Association for Computational Linguistics (NAACL), Rochester, New York, 2007. Elming, Jakob and Nizar Habash. Combination of Statistical Word Alignments Based on Multiple Preprocessing Schemes, In Proceedings of the North American chapter of the Association for Computational Linguistics (NAACL), Rochester, New York, 2007. Habash, Nizar and Owen Rambow. Morphophonemic and Orthographic Rules in a Multi- Dialectal Morphological Analyzer and Generator for Arabic Verbs, International Symposium on Computer and Arabic Language (ISCAL), Riyadh, Saudi Arabia, 2007. Habash, Nizar. “Arabic Morphological Representations for Machine Translation.” Book Chapter. In Arabic Computational Morphology: Knowledge-based and Empirical Methods. Editors Antal van den Bosch and Abdelhadi Soudi. 2007.
Habash, Nizar, Abdelhadi Soudi, and Tim Buckwalter. “On Arabic Transliteration.” Book Chapter. In Arabic Computational Morphology: Knowledge-based and Empirical Methods. Editors Antal van den Bosch and Abdelhadi Soudi. 2007. 2006Biadsy, Fadi, Jihad El-Sana and Nizar Habash. Arabic Online Handwriting Recognition. International Workshop on Handwriting and Optical Character Recognition, Paris, France, 2006.
Habash, Nizar, Bonnie Dorr and Christof Monz. Challenges in Building an Arabic Generation-heavy Machine Translation System and Extending it with Statistical Components. In Proceedings of the Association for Machine Translation in the Americas (AMTA-2006), Boston, MA, 2006.
Habash, Nizar. “On Arabic and its Dialects,” Multilingual Magazine. #81 Volume 17 Issue 5, 2006.
Habash, Nizar and Owen Rambow. Morphological Analysis for Arabic Dialects. In Proceedings of COLING-ACL, Sydney, Australia, 2006.
Sadat, Fatiha and Nizar Habash. Morphological Preprocessing Scheme Combination for Statistical MT. In Proceedings of COLING-ACL, Sydney, Australia, 2006.
Habash, Nizar and Fatiha Sadat. Arabic Preprocessing Schemes for Statistical Machine Translation, In Proceedings of the North American chapter of the Association for Computational Linguistics (NAACL), New York, 2006.
Chiang, David, Mona Diab, Nizar Habash, Owen Rambow, and Safi Shareef. Arabic Dialect Parsing. In Proceedings of the European chapter of the Association of Computational Linguistics (EACL). 2006.
Habash, Nizar, Clinton Mah, Randy Calistri-Yeh, Sabiha Imran and Paraic Sheridan. The Design and Validation of an Arabic WordNet for Information Retrieval. In Proceedings of the International Conference on Language Resources and Evaluation (LREC). 2006.
Rambow, Owen, Bonnie Dorr, David Farwell, Rebecca Green, Nizar Habash, Stephen Helmreich, Eduard Hovy, Lori Levin, Carnegie Keith J. Miller, Teruko Mitamura, Florence Reeder, Advaith Siddharthan. Parallel Syntactic Annotation of Multiple Languages. In Proceedings of the International Conference on Language Resources and Evaluation (LREC). 2006.
Passonneau, Rebecca, Nizar Habash and Owen Rambow. Interannotator Agreement on a Multilingual Semantic Annotation Task. In Proceedings of the International Conference on Language Resources and Evaluation (LREC). 2006.
Maamouri, Mohamed, Ann Bies, Tim Buckwalter, Mona Diab, Nizar Habash, Owen Rambow, Dalila Tabessi. Developing and Using a Pilot Dialectal Arabic Treebank. In Proceedings of the International Conference on Language Resources and Evaluation (LREC). 2006. 2005Habash, Nizar, Owen Rambow and George Kiraz. Morphological Analysis and Generation for Arabic Dialects. In Proceedings of the Workshop on Computational Approaches to Semitic Languages at the Conference of American Association for Computational Linguistics (ACL’05).
Habash, Nizar and Owen Rambow. Arabic Tokenization, Morphological Analysis, and Part-of-Speech Tagging in One Fell Swoop. In Proceedings of the Conference of American Association for Computational Linguistics (ACL’05).
Darwish, Kareem, Mona Diab and Nizar Habash, Eds. Computational Approaches to Semitic Languages. Workshop Proceedings. Association for Computational Linguistics, Ann Arbor, Michigan, 2005. PDF 2004Habash, Nizar. The Use of a Structural N-gram Language Model in Generation-Heavy Hybrid Machine Translation. In Proceedings of the Third International Conference of Natural Language Generation (INLG-04). Careys Manor, UK, July 2004.
Habash, Nizar. Large Scale Lexeme Based Arabic Morphological Generation. In Proceedings of Traitement Automatique du Langage Naturel (TALN-04). Fez, Morocco, 2004.
Habash, Nizar and Owen Rambow. Extracting a Tree Adjoining Grammar from the Penn Arabic Treebank. In Proceedings of Traitement Automatique du Langage Naturel (TALN-04). Fez, Morocco, 2004.
Habash, Nizar, Bonnie Dorr, Eduard Hovy, Florence Reeder. Eds. Determining Interlingua Utility for Machine Translation. Seventh Interlingua Workshop. Sixth Biennial Conference of the Association for Machine Translation in the Americas (AMTA-04). Georgetown, Washington DC, 2004. PDF
Ayan, Fazil, Bonnie J. Dorr, and Nizar Habash, Application of Alignment to Real-World Data: Combining Linguistic and Statistical Techniques for Adaptable MT. In Proceedings of the 6th Conference of the Association for Machine Translation in the Americas (AMTA-2004), Georgetown University, Washington DC, 2004.
Reeder, Florence, Bonnie Dorr, David Farwell, Nizar Habash, Stephen Helmreich, Eduard Hovy, Lori Levin, Teruko Mitamura, Keith Miller, Owen Rambow, Advaith Siddharthan. Interlingual Annotation for MT Development. In Proceedings of the 6th Conference of the Association for Machine Translation in the Americas (AMTA-2004), Georgetown University, Washington DC, 2004.
Farwell, David, Stephen Helmreich, Bonnie J. Dorr, Nizar Habash, Florence Reeder, Keith Miller, Lori Levin, Teruko Mitamura, Eduard Hovy, Owen Rambow, and Advaith Siddharthan. Interlingual Annotation of Multilingual Text Corpora. In Proceedings of the North American Chapter of the Association for Computational Linguistics Workshop on Frontiers in Corpus Annotation, Boston, MA, pp. 55--62, 2004.
Mitamura, Teruko, Keith J. Miller, Bonnie J. Dorr, David Farwell, Nizar Habash, Lori Levin, Stephen Helmreich, Eduard Hovy, Lori Levin, Owen Rambow, Reeder, Florence, and Advaith Siddharthan. Semantic Annotation of Multilingual Text Corpora. In Proceedings of the Workshop on Beyond Named Entity Recognition: Semantic Labeling for NLP Tasks, LREC, Portugal, 2004.
Dorr, Bonnie J., Rebecca Green, Lori Levin, Owen Rambow, David Farwell, Nizar Habash, Stephen Helmreich, Eduard Hovy, Keith J. Miller, Teruko Mitamura, Florence Reeder, and Advaith Siddharthan. Semantic Annotation and Lexico-Syntactic Paraphrase. In Proceedings of the Workshop on Building Lexical Resources from Semantically Annotated Corpora, LREC, Portugal, 2004. 2003 Dorr, Bonnie J., Necip Fazil Ayan, Nizar Habash, Nitin Madnani, and Rebecca Hwa. Rapid Porting of DUSTer to Hindi. ACM Transactions on Asian Language Information Processing (TALIP), 2:3, 2003.
Habash, Nizar. Matador: A Large Scale Spanish-English GHMT System. In Proceedings of the MT Summit, New Orleans, LA, pp. 149--156, 2003.
Cavalli-Sforza, Violetta, Alon Lavie and Nizar Habash. Eds. Proceedings of the MT Summit IX Workshop on Machine Translation for Semitic Languages: Issues and Approaches. September 23, 2003, New Orleans, LA, USA. URL
Habash, Nizar. Generation-Heavy Hybrid Machine Translation. Doctoral Dissertation. Computer Science Department, University of Maryland College Park, 2003.
Habash, Nizar and Bonnie Dorr, A Categorial Variation Database for English, Proceedings of North American Association for Computational Linguistics, Edmonton, Canada, pp. 96--102, 2003.
Habash, Nizar, Bonnie Dorr, and David Traum. Hybrid Natural Language Generation from Lexical Conceptual Structures. MT Journal volume 18 (2): 81-128, 2003. 2002 Habash, Nizar and Bonnie Dorr. Handling Translation Divergences: Combining Statistical and Symbolic Techniques in Generation-Heavy Machine Translation. In Proceedings of the Fifth Conference of the Association for Machine Translation in the Americas, AMTA-2002, Tiburon, CA, 2002.
Dorr, Bonnie and Nizar Habash. Interlingua Approximation: A Generation-Heavy Approach. In Proceedings of Workshop on Interlingua Reliability, Fifth Conference of the Association for Machine Translation in the Americas, AMTA-2002,Tiburon, CA, 2002.
Dorr, Bonnie, Lisa Pearl, Rebecca Hwa and Nizar Habash. DUSTer: A Method for Unraveling Cross-Language Divergences for Statistical Word-Level Alignment. In Proceedings of the Fifth Conference of the Association for Machine Translation in the Americas, AMTA-2002, Tiburon, CA, 2002.
Habash, Nizar. Generation-Heavy Hybrid Machine Translation. In Proceedings of the International Natural Language Generation Conference (NLG-02). New York, 2002. 2001 Habash, Nizar and Bonnie Dorr. Large Scale Language Independent Generation Using Thematic Hierarchies. In Proceedings of the MT Summit VIII. Santiago de Compostella, Spain. 2001. 2000 Habash, Nizar. oxyGen: A Language Independent Language Realization Engine. In Proceedings of the Fourth Conference of the Association for Machine Translation in the Americas, AMTA-2000. Cuernavaca, Mexico.
Traum, David and Nizar Habash. Generation from Lexical Conceptual Structures. Workshop on Applied Interlinguas, ANLP-2000. Seattle, WA. 1999 Habash, Nizar. Nuun: A System for Developing Platform and Browser Independent Arabic Web Applications. In Proceedings of the Arabic Translation and Localization Conference (ATLAS-99). Tunis, Tunisia, 1999. Republished in Arabic in the Arab Journal of Science, 33, June 1999.
Habash, Nizar. Issues in Palestinian Arabic Spelling Standardization. NACAL 27, 1999. Baltimore, MD. 1998 Dorr, Bonnie, Nizar Habash and David Traum. A Thematic Hierarchy for Efficient Generation from Lexical-Conceptual Structures. In Proceedings of the Association of Machine Translation in the Americas, AMTA-98. Longhorne, PA.
Habash, Nizar. Introduction to Delason: The Complete Guide to the Artificial Language. Unpublished Manuscript, 1998.
Technical Reports 2005Rambow, O., D. Chiang, M. Diab, N. Habash, R. Hwa, K. Sima’an, V. Lacey, R. Levy, C. Nichols, and S. Shareef.. Parsing Arabic Dialects. Final Report, JHU Summer Workshop. 2005. 2004 Bonnie J. Dorr, Nizar Habash and Christof Monz. Symbolic MT with Statistical NLP Components. Technical Report: LAMP-TR-112/CS-TR-4595/UMIACS-TR-2004-38, University of Maryland, College Park, June 2004. (PDF)
Bonnie J. Dorr, Nizar Habash and Christof Monz. Use of Minimal Lexical Conceptual Structures for Single-Document Summarization. Technical Report: LAMP-TR-113/CS-TR-4596/UMIACS-TR-2004-39, University of Maryland, College Park, June 2004. (PDF) 2003 Nizar Habash and Bonnie Dorr. A Categorial Variation Database for English. Technical Report: LAMP-TR-095/CS-TR-4443/UMIACS-TR-2003-13, University of Maryland, College Park, 2003. (PDF) Habash, Nizar and Jin Tong. MFTV: A Zoomable Multifaceted Tree Viewer. Technical Report, CS-TR-4528. Computer Science Department. University of Maryland College Park. 2003. PDF 2002 Bonnie J. Dorr, Lisa Pearl, Rebecca Hwa and Nizar Habash. Improved Word-Level Alignment: Injecting Knowledge about MT Divergences. Technical Report: LAMP-TR-082/CS-TR-4333/UMIACS-TR-2002-15, University of Maryland, College Park, February 2002. (PDF)
Nizar Habash and Bonnie Dorr. Handling Translation Divergences in Generation-Heavy Hybrid Machine Translation. Technical Report: LAMP-TR-083/CS-TR-4341/UMIACS-TR-2002-23, University of Maryland, College Park, March 2002. (PDF)
Nizar Habash and Bonnie Dorr. Handling Translation Divergences: Combining Statistical and Symbolic Techniques in Generation-Heavy Machine Translation. Technical Report: LAMP-TR-088/CS-TR-4369/UMIACS-TR-2002-49, University of Maryland, College Park, May 2002. (PDF) 2001 Nizar Habash, Bonnie Dorr and David Traum. Efficient Language Independent Generation from Lexical Conceptual Structure. Technical Report: LAMP-TR-074/CS-TR-4262/UMIACS-TR-2001-43, University of Maryland, College Park, September 2001. (PDF)
Nizar Habash and Bonnie Dorr. Large Scale Language Independent Generation Using Thematic Hierarchies. Technical Report: LAMP-TR-075/CS-TR-4280/UMIACS-TR-2001-59, University of Maryland, College Park, September 2001. (PDF)
Nizar Habash. Nuun: A System for Developing Platform and Browser Independent Arabic Web Applications. Technical Report: LAMP-TR-076/CS-TR-4281/UMIACS-TR-2001-60, University of Maryland, College Park, September 2001. (PDF)
David Traum and Nizar Habash. Generation from Lexical Conceptual Structures. Technical Report: LAMP-TR-077/CS-TR-4282/UMIACS-TR-2001-61, University of Maryland, College Park, September 2001. (PDF)
Nizar Habash. A Reference Manual to the Linearization Engine oxyGen Version 1.6. Technical Report: LAMP-TR-079/CS-TR-4295/UMIACS-TR-2001-73, University of Maryland, College Park, October 2001. (PDF) 2000 Nizar Habash. Oxygen: A Language Independent Linerization Engine. Technical Report: LAMP-TR-042/CS-TR-4144/UMIACS-2000-35, University of Maryland, College Park, June 2000. (PDF) 1998 Bonnie J. Dorr, Nizar Habash and David Traum. A Thematic Hierarchy for Efficient Generation from Lexical-Conceptual Structure. Technical Report: LAMP-TR-022/UMIACS-TR-98-50/CS-TR-3934, University of Maryland, College Park, October 1998. (PDF)
Posters, Presentations and Panels
2007
Diab, Mona, Mahmoud Ghoneim, Nizar Habash, Impact of Partial Arabic Diacritization on Statistical Machine Translation. NLP Colloquium, Columbia University. 2007.
Elming, Jakob and Nizar Habash, Improving Word Alignment through Combination of Multiple Preprocessing Schemes. NLP Colloquium, Columbia University. 2006.
Habash, Nizar, Morphological Preprocessing for Statistical Machine Translation. NLP Colloquium, Columbia University. 2006.
Diab, Mona, Mahmoud Ghoneim, Nizar Habash, Impact of Partial Arabic Diacritization on Statistical Machine Translation. Invited Presentation, GALE PI Meeting, San Francisco. 2007.
Habash, Nizar and Owen Rambow, Arabic Diacritization through Full Morphological Tagging. Invited Presentation, GALE PI Meeting, San Francisco. 2007.
Kirchhoff, Katrin, Nizar Habash, Mona Diab, Owen Rambow, Evgeny Matusov, Semi-Automatic Error Analysis of the NIGHTINGALE Machine Translation System. Invited Presentation, GALE PI Meeting, San Francisco. 2007.
Habash, Nizar and Jakob Elming, Improving Word Alignment through Combination of Multiple Preprocessing Schemes. Invited Presentation, GALE PI Meeting, San Francisco. 2007.
Habash, Nizar, Halim Abbas, Bonnie Dorr, Christof Monz and Necip Ayan. Columbia University 2006 Arabic-English MT Evaluation Systems. NIST Machine Translation 2006 (MT-06) Evaluation. September, 2006.
Member of a Panel on Hybrid Machine Translation. The Association for Machine Translation in the Americas (AMTA-2006), Boston, MA, 2006.
2006 Habash, Nizar, Fatiha Sadat, George Forster and Roland Kuhn. Arabic Preprocessing Schemes for Statistical Machine Translation. Invited Presentation, 2nd GALE PI Meeting, Boston. 2006.
Mona Diab, Habash, Nizar, and Owen Rambow. NLP Tools for Arabic. Invited Presentation, 2nd GALE PI Meeting, Boston. 2006. 2005 Habash, Nizar. Sentence Tansduction. In Rambow et al, Arabic Dialect Parsing: Final Presentaion. Johns Hopkins Summer Workshop, Baltimore, August 17, 2005. PDF
David Chiang, Bonnie Dorr, Nizar Habash, Christof Monz and Philip Resnik, and. The University of Maryland College Park 2005 Chinese-English and Arabic-English MT Evaluation Systems. NIST Machine Translation 2005 (MT-05) Evaluation. June, 2005. 2004 Habash, Nizar. Generation Heavy Hybrid Machine Translation. NLP group colloquium. Columbia University. October 28, 2004.
Habash, Nizar. Workshop Task Description and Results. AMTA’04 Seventh Interlingua Workshop Determining Interlingua Utility for Machine Translation Georgetown University, Washington DC, October 2, 2004 PPT
Kumar, Shankar, Yonggang Deng, Charles Schafer, Woosung Kim, Paola Virga, Nizar Habash, David Smith, Filip Jurcicek, Bill Byrne, Sanjeev Khudanpur, Zak Shafran, and David Yarowsky. The Johns Hopkins University 2004 Chinese-English and Arabic-English MT Evaluation Systems. NIST Machine Translation 2004 (MT-04) Evaluation. June 22, 2004. PDF
S. Helmreich, D. Farwell, B. Dorr, N. Habash, L. Levin, T. Mitamura, F. Reeder, K. Miller, E. Hovy, O. Rambow and A. Siddharthan. Invited Talk: Interlingual Annotation of Multilingual Text Corpora. In The Workshop on Frontiers in Corpus Annotation. HLT-NAACL Conference, Boston, Massachusetts, May 6, 2004. HTML
Madnani, Nitin, Necip Fazil Ayan, Bonnie Dorr, Nizar Habash and Christof Monz. Portable Divergence Unraveling: The Case of Hindi. Poster Presentation. TECH 2004. University of Maryland College Park. March 19, 2004. HTML
Habash, Nizar. Aragen: Large Scale Arabic Morphological Generation. Poster Presentation. TECH 2004. University of Maryland College Park. March 19, 2004. HTML
Habash, Nizar and Omer Horvitz. What it's like to be a grad student. Invited Talk. CMSC 838I: How to do Research. March 8, 2004. (Syllabus) 2003 Habash, Nizar. Matador: Spanish-English GHMT. System Demonstration. In Proceedings of the MT Summit, New Orleans, LA, pp. 467--470, 2003.
Habash, Nizar and Bonnie Dorr. CatVar: A Database of Categorial Variations for English. System Demonstration. In Proceedings of the MT Summit, New Orleans, LA, pp. 471--474, 2003. Habash, Nizar. Palisra: Conflict Resolution As Art. Invited Talk. GVPT 309X: Topics in International Relations: Conflict Resolution - The Israeli Palestinian Experiment. University of Maryland College Park , 2003. 2002 Habash, Nizar and Bonnie Dorr. Interlingua Annotation Experiment Results. AMTA-2002 Interlingua Reliability Workshop. Tiburon, California, USA.
Dorr, Bonnie, Nizar Habash and David Zajic. Generation-Heavy MT and Headline Generation. LAMP II Kickoff Meeting. June 7, 2002.
Dorr, Bonnie and Nizar Habash. Lexical Representation in Chinese-English Machine Translation. Poster Presentation. UMIACS Research Review Day 2002. (List of Posters)
Habash, Nizar. Generation Heavy Machine Translation. UMIACS Computational Linguistics Colloquium Series. February 27, 2002. 2001 Habash, Nizar. Large Scale Language Independent Generation Using Thematic Hierarchies. UMIACS Computational Linguistics Colloquium Series. September 6, 2001.
Habash, Nizar. Evaluation of Machine Translation. Workshop on Evaluation of Interactive Cross-Language Information Retrieval. Human-Computer Interaction Laboratory. University of Maryland. May 31, 2001.
Habash, Nizar and Bonnie Dorr. Efficient Natural Language Translation: Language Independent Generation Using the Realization Engine oxyGen. Poster Presentation. UMIACS Research Review Day 2001.
Habash, Nizar. Cold Fusion: Semantic Composition without Syntactic Parsing. UMIACS Computational Linguistics Colloquium Series. March 14, 2001.
Habash, Nizar. Improvements to Oxygen Generation System. Laboratory for Language and Media Processing, Interim Project Review. University of Maryland College Park, January 24, 2001.
Habash,
Nizar. ChinMT Generation.
Laboratory for Language and Media Processing, Interim Project Review. University of Maryland College Park, January 24, 2001. 2000 Habash, Nizar. oxyGen: A Language Independent Linearization Engine. UMIACS Computational Linguistics Colloquium Series. October 4, 2000. CALL
Habash, Nizar. Panelist/Presemter: The Fourth Special Interest Group on Interlinguas and Interlingual Approaches Workshop. Association for Machine Translation in the Americas (AMTA), Cuernavaca, Mexico, 2000. URL
Habash, Nizar. Generation Status. Laboratory for Language and Media Processing, Interim Project Review. University of Maryland College Park, June 28, 2000. 1999 Habash, Nizar. Oxygen. Laboratory for Language and Media Processing, Interim Project Review. University of Maryland College Park, December 2, 1999.
Traum, David and Nizar Habash. Generation Overview. Laboratory for Language and Media Processing, Interim Project Review. University of Maryland College Park, December 2, 1999.
Habash, Nizar and Jin Tong. MFTV: A Zoomable Multifaceted Tree Viewer. Poster Presentation. UMIACS Research Review Day 1999.
Dorr, Bonnie, and Nizar Habash and David Traum. Broad- scale Lexical Representations for Multilingual Systems. Poster Presentation. National Science Foundation Workshop on Human-Computer Interaction, Florida 1999. 1998 Habash, Nizar. A Thematic Hierarchy for Efficient Generation from Lexical-Conceptual Structure. UMIACS Computational Linguistics Colloquium Series. October 15, 1998.
Invited Talks 2007
Habash, Nizar. Arabic Diacritization through Full Morphological Tagging. Invited Talk, Language Technology Institute Seminar Series. Carnegie Mellon University, 2007. 2006 Habash, Nizar. Arabic Dialect Modeling: form Morphological Analysis to Parsing. Invited Talk, NSF Funded US-Morocco Workshop on Language Technology Research and Education. Ecole Nationale de l'Industrie Minérale (Rabat, Morocco) May 29 - June 2, 2006.
Habash, Nizar. Disambiguation of Rich Arabic Morphological Analyses. Invited Talk, NYU Natural Language Processing Colloquium. April 14, 2006. 2005 Mona Diab, Nizar Habash, and Owen Rambow. Arabic Dialect Parsing. Invited Talk, Linguistic Data Consortium, University of Pennsylvania, December 9, 2005
Habash, Nizar. Combining Symbolic and Statistical Techniques for Machine Translation and Morphological Disambiguation. Invited Talk, AT&T Labs, Florham Park, NJ, October 7, 2005.
Habash, Nizar. Generation-Heavy Hybrid Machine Translation. Invited Talk. IBM TJ Watson Research Center, March 9, 2005.
Habash, Nizar. Generation-Heavy Hybrid Machine Translation. Invited Talk. Computer Science Department Seminar, City College of New York, March 8, 2005. 2004 Habash, Nizar. Generation-Heavy Hybrid Machine Translation. Invited Talk. Language Technologies Institute Seminar. Carnegie Mellon University, November 19, 2004. 2003 Habash, Nizar. Semitic Linguistic Phenomena. Invited Talk. Workshop on Machine Translation for Semitic Languages, MT Summit, New Orleans, LA, 2003. Announcement
Software · |