Servicios Personalizados
Revista
Articulo
Indicadores
- Citado por SciELO
- Accesos
Links relacionados
- Similares en SciELO
Compartir
Polibits
versión On-line ISSN 1870-9044
Polibits no.37 México ene./jun. 2008
Special section: natural language processing
Methods for Handling Spontaneous Ecommerce Arabic SMS: CATS, an Operational Proof of Concept
Maher Daoud1 and Christian Boitet2
1 University, PoBox 141009, Zip Code 11814, Amman Jordan. (Daoud@batelco.jo, Daoud.Daoud@imag.fr)
2 GETALP, LIG, Université Joseph Fourier, 385 rue de la Bibliothèque, BP no 53, 38041 Grenoble, cedex 9, France (email: Christian.Boitet@imag.fr)
Manuscript received May 2, 2008.
Manuscript accepted for publication June 18, 2008.
Abstract
The purpose of this paper is to show that it is necessary and possible to build (multilingual) NLbased ecommerce systems with mixed sublanguage and contentoriented methods. The analysis of the sublanguage and the integration of contentoriented methods will definitely increase the accuracy and robustness of the processing. To verify this assumption, we built an experimental system as a proof of concept. The system is a SMSbased classified ads selling and buying platform. To analyze the sublanguage, we first used a web based corpus to build the basic system. A content representation language is defined to capture the meaning of a classified ad post. The semantic grammars of content extraction are coded using the EnCo. Response generation is based on semantic matching ("looking for" and "sell" posts) and reasoning and is able to handle "no answer situations". CATS is currently deployed in Jordan by Fastlink (the largest mobile operator). Testing the content extraction component with a real noisy free texts shows a 90% Fmeasure.
Key words: Spontaneous NL interface, SMS services, sublanguages, content extraction, classified ads, Arabic processing.
DESCARGAR ARTÍCULO EN FORMATO PDF
REFERENCES
[1] MKBEEM, "(web site)," 2005. [ Links ]
[2] J. Heinecke and F. Toumani, "A Natural Language Mediation System for ECommerce applications: an ontologybased approach," presented at Workshop on Human Language Technology for the Semantic Web and Web Services,2nd International Semantic Web Conference, Sanibel Island, Florida, 2003. [ Links ]
[3] A. Lehtola, Y. KÄPYLÄ, C. BOUNSAYTHIP, and M. TALLGREN, "Multilingual and Ontological Product Cataloguing Tool User Experiences," presented at eChallenges2003 Building the Knowledge Economy: Issues, Applications, Case Studies., Bologna, Italy, 2003. [ Links ]
[4] A. Lehtola, C. Bounsaythip, and J. Tenni, "Controlled Language Technology in Multilingual User Interfaces," presented at 4th ERCIM Workshop on "User Interfaces for All" Special Theme "Towards an Accessible Web", Stockholm, Sweden, 1998. [ Links ]
[5] A. Lehtola, J. Tenni, C. Bounsaythip, and a. K. Jaaranen, "WEBTRAN: A Controlled Language Machine Translation System for Building Multilingual Services on Internet ", vol. 2006, 1999. [ Links ]
[6] P. Buitelaar, K. Netter, and F. Xu, "Integrating Different Strategies for CrossLanguage Information Retrieval in the MIETTA Project," presented at TWLT14, Enschede, Netherlands, 1998. [ Links ]
[7] H. Somers, B. Black, J. Nivre, T. Lager, A. Multari, L. Gilardoni, J. Ellman, and A. Rogers, "Multilingual Generation and Summarization of Job Adverts: the TREE Project," presented at Fifth Conference on Applied Natural Language Processing, Washington, DC, 1997. [ Links ]
[8] J. Chai, V. Horvath, N. Nicolov, M. Stys, N. Kambhatla, W. Zadrozny, and P. Melville, "Natural Language Assistant A Dialog System for Online Product Recommendation," AI Magazine, vol. 23, pp. 6375, 2002. [ Links ]
[9] X. Gao and L. Sterling, "Classified Advertisement Search Agent (CASA): a knowledgebased information agent for searching semistructured text." presented at Third International Conference on the Practical Application of Intelligent Agents and MultiAgent Technology, 1998. [ Links ]
[10] R.I. Kittredge:, "Sublanguages," American Journal of Computational Linguistics, vol. 8, pp. 7984, 1982. [ Links ]
[11] F. Benamara, "Cooperative Question Answering in Restricted Domains: the WEBCOOP Experiment," presented at ACL'04 Workshop on Question Answering in Restricted Domains, Barcelona, 2004. [ Links ]
[12] D. Moldovan, C. Clark, S. Harabagiu, and S. Maiorano, "COGEX: A Logic Prover for Question Answering," presented at HLTNAACL 2003, Edmonton, 2003. [ Links ]
[13] S. Sekine, "The Domain Dependence of Parsing", presented at Applied Natural Language Processing (ANLP'97), Washington D.C., USA, 1997. [ Links ]
[14] J. Lehrberger, "Automatic Translation and the Concept of Sublanguage," in Sublanguage: Studies of Language in Restricted Semantic Domains, R. Kittredge and J. Lehrberger, Eds. Berlin & New York: Walter de Gruyter, 1982, pp. 81106. [ Links ]
[15] A. Goweder and A. De Roeck, "Assessment of a significant Arabic corpus," presented at Arabic NLP Workshop at ACL/EACL 2001, Toulouse, France, 2001 [ Links ]