Svetlana Sheremetyeva

Doctor of Sciences (PhD. Habilitation)
    In Computational Linguistics
M.Sc. (Magna cum laude)
    in Mathematics and English
Professor of South Ural State University, Chelyabinsk, Russia
Tel.: +7 351 267 98 45/ +7 351 65 06 91;  Fax +7 351 267 98 45
e-mail: lanalink@yahoo.com
Adjunct professor, Department of International Language Studies and Computational Linguistics, Copenhagen Business School, Denmark;
Project leader, LanA Consulting ApS, Copenhagen, Denmark.
Tel.: +45 51 22 34 58/ +45 20 15 28 44;
e-mail: lanaconsult@mail.dk
Member of the European Association for Machine Translation (EAMT).
Program and organizing committees member of many EAMT and MT-SUMMIT conferences, tutorials and workshops.
Current and Future activities as EAMT member:
- Program committee member of the EAMT-2011 conference, Leuven, Belgium, 30-31 May, 2011
- Director and lecturer of the joint EAMT-SUSU Intensive School in Machine Translation, Chelyabinsk Russia, 16-20 April, 2011
- Co-organizer of MT-SUMMIT XIV, Nice, France, September 2013






My Tools for
teaching, research
and business
activities


Lexicon Creator


Tagger


SMAT


Term


LanA-Key


AutoPat


AutoTrans


AutoRead


AutoTree-C

Research and Teaching
My experience in MT and CL (computational linguistics) research and teaching was accumulated during my postgraduate course in CL at St.Petersburg State University followed by many years of work as Head of Foreign Language Department and Professor of Linguistic Department at South Ural State University (Russia), postdoc study at Montreal University, work as Key Researcher at the Computing Research Lab of New Mexico State University (USA), lecturer in CL and MT at Uppsala University (Sweden) and Copenhagen Business School (Denmark), as well as different international Summer schools, e.g., Summer School in Language Engineering (USA) and NATO Advanced Study Institute on Language Engineering for Lesser Studied Languages (Turkey).

Conference Organizing
I was a program committees member, organizer and co-organizer of different international conferences, such as EAMT-2010 (France), IPWARE SUMMIT-2009 (France), workshops in conjunction with MT-SUMMIT 2007 (Denmark), the workshop "Analysis for Generation" in conjunction with The International Conference on NLG (Israel), Summer School in Language Engineering (USA), the workshop "Minimizing the Effort for Language Resource Acquisition" in conjunction with The First LREC (Spain), etc.

More details on teaching
The disciplines I have taught (and teach) at all levels of higher education (bachelor, master and Ph.D.) include MT for developers, MT for translators, formal syntax, computational morphology, computational lexicography, natural language analysis and generation, summarization. I am a supervisor of undergraduate students' course and diploma papers and post-graduate students' PhD thesis research.

Teaching my courses abroad Russia and being a member of EAMT I have always tried to do my best to contribute to the international cooperation between foreign universities and Southern Ural State University, organizing student exchange, e.g., to CRL NMSU and CBS, joint research, e.g., CBS-based MT-project, and educational projects, ISMT, for which I got a joint EAMT-SUSU grant, being the most recent.

More details on research
My research interests cover several areas of natural language processing (NLP), notably, but not exclusively - machine translation, sublanguage analysis, multilingual text generation, knowledge design and acquisition for unilingual/multilingual NLP and domain-tuned applications, in particular, applications for processing patent information. I focus on the issue of saving effort in text processing systems development and concentrate on multipurpose linguistic software development for practical real-world use.

A brief summary of my recent efforts and results are as follows. I have concentrated on the development of quality IP related software in the frame of national and international/joint projects in the USA, Japan, Russia and Denmark. The range of IP oriented tools developed under my supervision cover major aspects of IP-related activities: knowledge management, case handling, keyword extraction, search, patent claim analysis, patent claim composition and machine translation of patents, terminological Internet/PC database, etc. I also developed a number of tools for linguistic research and training computational linguists and translators.

I developed a novel method for morphological analysis without a stem dictionary and implemented it in broad-coverage morphological analyzers for both Russian and Serbo-Croatian. I am quite comfortable in carrying out research on languages that are new to me. For instance, when at CRL NMSU (USA) I have developed a component of a computational grammar for Turkish for use in a Turkish-English machine translation system. I also participated in MikroKosmos ontology development and led a group of ontology and ontology based multi-lingual lexicon acquirers.

 
List of Publications

1. Sheremetyeva S., Dymin N., and Mylarschikova T. 2010. On Cross-Linguistic Portability Of Text Processing Systems. Proceedings of the Fifth International Conference "Computational Linguistics in Science and Education" St.Petersburg, Russia. March 28-30.
2. Sheremetyeva S. 2009. Software for Processing Patent Claims. Proceedings of IPWARE SUMMIT-2009, St.Raphael, France.
3. Sheremetyeva S. 2009. An Efficient Patent Keyword Extractor As Translation Resource Proceedings of the 3rd Workshop on Patent Translation in conjunction with MT-Summit XII Ottawa, Canada
4. Sheremetyeva S. 2009 On Extracting Multiword NP Terminology for MT. Proceedings of the Thirteen Conference of European Association of Machine Translation (EAMT-2009). Barcelona, Spain. May 14-15.
5. Шереметьева. 2009. Automatic Text Processing in Distant Language Learning. Proceedings of the Third International conference on Distant Language Learning. Perm. Russia. April 23-25.
6. Sheremetyeva S. 2008. On NLP Modules with Shared Knowledge for a Patent Workstation. Proceedings of the PATExpert Workshop for Patent experts and researchers. Stuttgart, Germany. 2008 June, 23-24.
7. Sheremetyeva S., Dymin N. 2008. On Universal Platform for Linguistic Software. Works of South Ural State University. Chelyabinsk, Russia.
8. Sheremetyeva S. 2007. On Portability of Resources for Quick Ramp-Up of Multilingual MT for Patent Claims. Proceedings of the workshop on Patent Translation in conjunction with MT Summit XI, Copenhagen, Denmark, September 10-14.
9. Sheremetyeva S. 2006. Integration of Correction Modules in a Controlled Language Application. Proceedings of the 5th International Workshop on Controlled Language Applications (CLAW) in conjunction with the 7th biennial conference of the Association for Machine Translation in the Americas (AMTA), August, 8-12.
10. Sheremetyeva S. 2006. Handling Low Translatability in Machine Translation. Proceedings of the Eleventh Conference of European Association of Machine Translation (EAMT). Oslo, Norway. June 19-20.
11. Sheremetyeva S. 2006.Understanding Long Sentences. Proceedings of the Third International workshop on Natural language Understanding and Cognitive Science in conjunction with International Conference on Enterprise (ICEIS) - 2006. Cyprus, Paphos, May, 23.
12. Sheremetyeva S. 2005. Embedding MT for Generation in English from a Multilingual Interface. Proceedings of the workshop on Patent Translation in conjunction with MT Summit X, Phuket, Thailand, September, 12-16.
13. Sheremetyeva S. 2005. "Less, Easier and Quicker" in Language Acquisition for Patent MT. Proceedings of the workshop on Patent Translation in conjunction with MT Summit X, Phuket, Thailand, September, 12-16.
14. Sheremetyeva S. 2005. Meaning-Text Theory for Textual Input Analysis and Proofing in a Generation System. Proceedings of the International Conference on Meaning-Text Theory. Moscow, Russia, June 23-25.
15. Sheremetyeva S. 2004. Application Adaptive Electronic Dictionary with Intelligent Interface. Proceedings of the workshop on Enhancing and using electronic dictionaries in conjunction with the 20th International Conference on Computational Linguistics. COLING 2004, Geneva, Switzerland, August, 23-28.
16. Sheremetyeva S. 2004. A Flexible Language Acquisition Tool Kit for Natural Language Processing. Proceedings of the Fourth International Conference on Lexical Resources and Evaluation (LREC 2004), Lisbon, Portugal, 24-30 May.
17. Sheremetyeva S. 2003. Natural Language Analysis of Patent Claims. Proceedings of the workshop "Patent Corpus Processing" in conjunction with 41st Annual Meeting of the Association for Computational Linguistics (ACL 2003), Sapporo. Japan, July 7-12.
18. Sheremetyeva S. Towards Designing Natural Language Interfaces. 2003. Proceedings of the 4th International Conference "Computational Linguistics and Intelligent Text Processing" Mexico City, Mexico, February 16-22.
19. Sheremetyeva S. 2002. An MT Learning Environment for Computational Linguistics Students. Proceedings of the 6th European Association for Machine Translation Workshop "Teaching Machine Translation", Manchester, England, November 14-15.
20. Sheremetyeva S.O., Pervuchin A.A.,Trotshenko V.N., Tkachev A.M. 2002. On Creating Metadata With Authoring Tools. Proceedings of the workshop "Semantic Authoring, Annotation and Markup" in conjunction with 15th European Conference on Artificial Intelligence, Lyon, France, July 21-26.
21. Sheremetyeva S.O. 2002. Computer-Aided Acquisition of Language Teaching Materials from Corpora. Proceedings of the fifth "Teaching and Large Corpora" conference. Bertinoro, Italy, July 26-31.
22. Sheremetyeva S, Pervuchin A.,Trotshenko V, Tkachev A. 2002. Towards Saving on Software Customization. Proceedings of the workshop "Customizing Knowledge in NLP Applications - Strategies, Issues and Evaluation" in conjunction with "Third International Conference on Language Resources and Evaluation", Las Palmas de Gran Canarias, Spain, May 28-31.
23. Sheremetyeva S. and S.Nirenburg. 2001. A Domain Tuned Tool for Multi-lingual Document Management. Proceedings of Israeli Seminar on Computational Linguistics. ISCOL'01. University of Hifa. February 15.
24. Sheremetyeva, S and S. Nirenburg. 2000. Towards A Universal Tool For NLP Resource Acquisition. Proceedings of LREC-2000 (Second International Conference on Language Resources and Evaluation) Athens, Greece., June
25. Nirenburg S., V. Ruskin and S. Sheremetyeva. 2000. Lexical Acquisition. Proceedings of NATO Advanced Science Institute on Lesser Studied Languages. Ankara, Turkey.
26. Cowie J., Ludovic E., H.Molino-Salgado, S.Nirenburg, and S.Sheremetyeva. Automatic Question Answering. Proceedings of the RIAO2000 Conference, Paris, France, April
27. Sheremetyeva, S. and S. Nirenburg. 1999. Knowledge Acquisition For Domain Information Management. Submitted to Computers and the Humanities. Special issue.
28. Ogdan B., Cowie J., Ludovic E., H., Molino-Salgado, S.Nirenburg, Nigel Sharples and Sheremetyeva, S. 1999. CRL's TREC-8 SystemsCross-Lingual IR, and Q&A. Proceedings of the Computing Research Laboratory, New Mexico State University, USA.
29. Sheremetyeva, S. 1999.A Flexible Approach To Multi-Lingual Knowledge Acquisition For NLG. 1999. Proceedings of the 7th European Workshop on Natural Language Generation. Toulouse. France. May 13-15.
30. Sheremetyeva, S. and S. Nirenburg. 1999. Interactive MT As Support For Non-Native Language Authoring. Proceedings of the MT Summit VII. September 13-17, 1999, Singapore.
31. Sheremetyeva, S., S. Nirenburg and W.-Y. Jin. 1999. Rapid Deployment Morphology. Machine Translation. March
32. Sheremetyeva, S. and S. Nirenburg. 1999. Porting a Rapid Development Morphological Analyzer Across Slavic Languages. Proceedings of the 8th Annual Workshop on Formal Approaches to Slavic Linguistics. Philadelphia. May 21-23.
33. Sheremetyeva, S. 1999. Cross-Linguistic Study and Interactive Acquisition of Argument Structure for a Restricted Domain Application. Proceedings of the 1999 conference of the Texas Linguistic Society on Perspectives on Argument Structure. Austin. March 5-7.
34. Sheremetyeva S., J. Cowie, S. Nirenburg and R. Zajac. Multilingual Onomasticon as a Multipurpose NLP Resource. 1998. Proceedings of the First International Conference on Language Resources and Evaluation, Granada, Spain, May.
35. Sheremetyeva, S. and S. Nirenburg. 1998.Two Experiments on Balancing the Acquisition Effort And Automation Levels With the Needs of an Application. Proceedings of the workshop Minimizing the Effort for Language Resource Acquisition in conjunction with The First International Conference on Language Resources and Evaluation, Granada, Spain, May.
36. Sheremetyeva S. 1998. Acquisition of Language Resources for Special Applications. Proceedings of the workshop Adapting Lexical and Corpus resources to Sublanguages and Applications in conjunction with The First International Conference on Language Resources and Evaluation, Granada, Spain, May.
37. Sheremetyeva, S. 1998. Computer-Aided Linguistic Knowledge Elicitation for Sublanguage Machine Translation. The Annual Conference of the American Association for Applied Linguistics. Seattle. March.
38. Sheremetyeva, S. 1998. Theoretical and Methodological Problems of Language Engineering. Submitted to Nauchno-Technicheskaja Informacija (Scientific and Technological Information), Series 2.
39. Sheremetyeva, S. 1998. Methodology of Minimizing Effort in Language Engineering. Submitted to Nauchno-Technicheskaja Informacija (Scientific and Technological Information), Series 2.
40. Sheremetyeva, S. and S. Nirenburg. 1997. Minimizing Acquisition and Development Effort in Computational Morphology. Proceedings of CLIN-97. Nijmegen. December.
41. Sheremetyeva, S. 1997. Methodology of Minimizing Effort in Language Engineering. Doctor of Sciences (Habilitation) Dissertation. St. Petersburg University, Russia, 465 pp.
42. Sheremetyeva S. and S. Nirenburg. 1996. Interactive Knowledge Elicitation in a Patent Expert's Workstation. IEEE Computer. Vol.7.
43. Sheremetyeva, S. and S. Nirenburg. 1996. Generating Patent Claims. Proceedings of the 8 International Workshop on Natural Language Generation. Herstmonceux, Sussex, UK.
44. Sheremetyeva, S. and S. Nirenburg. 1996. Russian Morphology with an Economy of Effort. Proceedings of DIALOGUE-96. Moscow. May.
45. Sheremetyeva, S.O. and S. Nirenburg. 1996. Empirical Modeling in Computational Morphology. Nauchno-Technicheskaja Informacija (Scientific and Technological Information), Series 2, Issue 7.
46. Sheremetyeva, S.O. and S. Nirenburg. 1996. From Interactive Elicitation of Knowledge to Realization of Automatic Synthesis of Patent Claims. 1996. Issue 11.
47. Sheremetyeva, S. 1995. Analyze du R?sum? de Brevets ? la Base de la Stratification du Lexique Orient? vers la TA. IV-es Journ?es Scientifiques Lexicomatique et Dictionariques. Lyon, France.
48. Sheremetyeva, S.O. and V.K. Saryan. 1994. Extraction and Formalization of Linguistic Knowledge. Nauchno-Technicheskaja Informacija (Scientific and Technological Information), Series 2, Issue 6.
49. Sheremetyeva, S. 1993. Typologie quantitative d'un sous-langage et traduction automatique. III Journ?es Scientifiques Lexicomatique et Dictionariques. Montreal. Canada.
50. Butorov, V.D. and S.O. Sheremetyeva. 1993. Semantico-Syntactic Statistical Characteristics of Predicates in a Patent Claim. In: A.S.Gerd. (ed.) Structural and Applied Linguistics. St.Petersburg University Press.
51. Sheremetyeva, S.O. and V.K. Saryan. 1991. An Approach to Automatic Translation of Invention Claims. Nauchno-Technicheskaja Informacija (Scientific and Technological Information), Series 2, Issue 6.
52. Sheremetyeva, S.O. 1990. Quantitative Typology of Scientific and Technological Text and Translation. Proceedings of Conference on Problems of Scientific and Technological Translation. Gorky, Russia.
53. Sheremetyeva, S.O. and V.K. Saryan. 1990. On Linguistic Support for a On-line System for Authoring Invention Claims. Nauchno-Technicheskaja Informacija (Scientific and Technological Information), Series 2, Issue 9.
54. Sheremetyeva, S.O. 1990. Modeling the Sublanguage of Professional Communication. Proceedings of Workshop on Problems of Languages for Professional Communication. Kiev, USSR.
55. Sheremetyeva, S.O. 1990. The Syntactic Stage of Automatic Synthesis of Text in a Constrained Sublanguage. Proceedings of Symposium on Linguistic Problems in Artificial Intelligence. Leningrad.
56. Sheremetyeva, S.O. 1990. Linguistic Aspects of Developing a Single Regional Information System and Problems of Information Services. Proceedings of Conference on Problems of Automating Information, Invention, Patenting and Licensing Activities. Odessa, USSR.
57. Sheremetyeva, S.O. 1989. Automatic Extraction of Grammatical Minimum for Teaching Foreign Languages at Colleges of Technology. Proceedings of Conference on Comprehensive Computerization of Instruction in Universities. Leningrad, Russia.
58. Sheremetyeva, S.O. 1989. Developing Teaching Programs in Foreign Languages. In: B.W. Peltzverger. (ed.): Computer Technology and Instruction in Universities. Chelyabinsk Technical University Press, Russia.
59. Sheremetyeva, S.O. 1989. An Approach to Automating Patent Documents. Proceedings of Conference on Problems of Scientific and Technological Translation. Gorky, Russia.
60. Sheremetyeva, S.O. 1988. Pragmatics of Text Syntax in Special-Purpose Communication. In: V.V. Bogdanov (ed.): Sentence and Text: Semantics, Pragmatics and Syntax. Leningrad State University Press.
61. Sheremetyeva, S.O. 1988. Using Semantico-Syntactic Nets for Developing On-line Technology, Operational Storage and Processing of Patents. Proceedings of National Conference on Patent and Licensing Studies and Organization of Foreign Trade in New Economic Circumstances. Odessa.
62. Sheremetyeva, S.O. 1988. Teaching Scientific and Technical Translation Taking into Account Sublanguages. Proceedings of Conference on Modern Methods of Processing Foreign-Language Information. Chelyabinsk.
63. Sheremetyeva, S.O. 1988. A Typology of Predicate Terms in USSR and US Patent Claims. In: A.P. Turbin (ed.): Typology of Scientific Texts. Chelyabinsk: University Press.
64. Sheremetyeva, S.O. and L.A. Borodkina. 1987. Inter-Stratal Organization of Text of a U.S. Patent Claim. In: A.P. Turbin (ed.): Inter-Stratal Organization of Natural Language Text. Chelyabinsk University Press.
65. Sheremetyeva, S.O. 1987. Statistical and Algorithmic Modeling of a Sublanguage Grammar. Proceedings of National Conference on Psychological Science and Practice. Novosibirsk, Russia.
66. Sheremetyeva, S.O. 1987. Optimization of the Selection of Lexical Equivalents on the Basis of Formal Criteria. Proceedings of Conference on Scientific and Technological Terminology and Translation. Chelyabinsk.
67. Sheremetyeva, S.O. 1986. A Model for Representing the Meaning of an Invention Claim Geared at Synthesizing its Text. Proceedings of National Conference on Problems of Development and Deployment of Intellectual Systems. Novosibirsk, Russia.
68. Butorov, V.D. and S.O. Sheremetyeva. 1985. An Algorithmic Analysis of an Invention Claim. Nauchno-Technicheskaja Informacija (Scientific and Technological Information), Series 2, Issue 7.
69. Sheremetyeva, S.O. 1985. A Model of Text Synthesis for Patent Claims. Ph.D. Dissertation. Leningrad State University. 230 pp.
70. Sheremetyeva, S.O. 1984. On Formal Synthesis of Invention Claims. Nauchno- Technicheskaja Informacija (Scientific and Technological Information), Series 2, Issue 5.
71. Sheremetyeva, S.O. 1984. Lexicographic Analysis of Predicate Terms. In: Ju.I.Ivashkin (ed.), Field Terminology and Lexicography. Voronezh University Press, Voronezh, Russia.
72. Sheremetyeva, S.O. 1984. Semantic Interpretation of the Invention Claim Text. Proceedings of the Conference on Psychological, Pedagogical and Linguistic Problems of Text Processing. Perm, Russia.
73. Sheremetyeva, S.O. 1984. On a Classification of Predicate Terms. Proceedings of Conference Scientific and Technical Information: Standardization, Translation and Editing. Chelyabinsk, Russia.