Communication with www in Czech

Lukáš Svoboda; Luboš Popelínský

Kybernetika (2004)

  • Volume: 40, Issue: 3, page [349]-363
  • ISSN: 0023-5954

Abstract

top
This paper describes UIO, a multi–domain question–answering system for the Czech language that looks for answers on the web. UIO exploits two fields, namely natural language interface to databases and question answering. In its current version, UIO can be used for asking questions about train and coach timetables, cinema and theatre performances, about currency exchange rates, name–days and on the Diderot Encyclopaedia. Much effort have been made into making addition of a new domain very easy. No limits concerning words or the form of a question need to be set in UIO. Users can ask syntactically correct as well as incorrect questions, or use keywords. A Czech morphological analyser and a bottom-up chart parser are employed for analysis of the question. The database of multiword expressions is automatically updated when a new item has been found on the web. For all domains UIO has an accuracy rate about 80

How to cite

top

Svoboda, Lukáš, and Popelínský, Luboš. "Communication with www in Czech." Kybernetika 40.3 (2004): [349]-363. <http://eudml.org/doc/33705>.

@article{Svoboda2004,
abstract = {This paper describes UIO, a multi–domain question–answering system for the Czech language that looks for answers on the web. UIO exploits two fields, namely natural language interface to databases and question answering. In its current version, UIO can be used for asking questions about train and coach timetables, cinema and theatre performances, about currency exchange rates, name–days and on the Diderot Encyclopaedia. Much effort have been made into making addition of a new domain very easy. No limits concerning words or the form of a question need to be set in UIO. Users can ask syntactically correct as well as incorrect questions, or use keywords. A Czech morphological analyser and a bottom-up chart parser are employed for analysis of the question. The database of multiword expressions is automatically updated when a new item has been found on the web. For all domains UIO has an accuracy rate about 80},
author = {Svoboda, Lukáš, Popelínský, Luboš},
journal = {Kybernetika},
keywords = {question answering; natural language processing; question answering; natural language processing},
language = {eng},
number = {3},
pages = {[349]-363},
publisher = {Institute of Information Theory and Automation AS CR},
title = {Communication with www in Czech},
url = {http://eudml.org/doc/33705},
volume = {40},
year = {2004},
}

TY - JOUR
AU - Svoboda, Lukáš
AU - Popelínský, Luboš
TI - Communication with www in Czech
JO - Kybernetika
PY - 2004
PB - Institute of Information Theory and Automation AS CR
VL - 40
IS - 3
SP - [349]
EP - 363
AB - This paper describes UIO, a multi–domain question–answering system for the Czech language that looks for answers on the web. UIO exploits two fields, namely natural language interface to databases and question answering. In its current version, UIO can be used for asking questions about train and coach timetables, cinema and theatre performances, about currency exchange rates, name–days and on the Diderot Encyclopaedia. Much effort have been made into making addition of a new domain very easy. No limits concerning words or the form of a question need to be set in UIO. Users can ask syntactically correct as well as incorrect questions, or use keywords. A Czech morphological analyser and a bottom-up chart parser are employed for analysis of the question. The database of multiword expressions is automatically updated when a new item has been found on the web. For all domains UIO has an accuracy rate about 80
LA - eng
KW - question answering; natural language processing; question answering; natural language processing
UR - http://eudml.org/doc/33705
ER -

References

top
  1. Appelt D. E., Israel D. J., Introduction to information extraction technology, In: Proc. 16th Internat. Joint Conference on Artificial Intelligence (IJCAI-99) Tutorial, Stockholm 1999 
  2. Aretoulaki M., Gallwitz F., Harbeck S., Ipšič I., Ivanecký J., Matoušek V., Niemann H., Nöth, E., Pavešič N., Sqel: A multilingual and multifunctional dialogue system, In: Proc. 5th Internat. Conference on Spoken Language Processing (ICSLP ’98), Sydney 1998, pp. 2883–2996 (1998) 
  3. Bauer D., Segond, F., Zaenen A., Enriching an sgml-tagged Dictionary for Machine-aided Comprehension, Technical Report No. MLTT-011, Rank Xerox Research Centre 1994 
  4. Bried E., Segond, F., Valetto G., Formal description of multiword lexemes with the finite-state formalism idarex, In: Proc. 16th Internat. Conference on Computational Linguistic. Morgan Kaufmann, San Francisco, CA 1996 
  5. Buchholz S., Daelemans W., Complex answers: a case study using a www question answering system, Natur. Language Engrg. 7 (2001), 4, 301–323 
  6. Clarke C., Cormack G., Kisman, D., Lynam T., Question answering by passage selection (multitext experiments for trec-9), In: Proc. Ninth Text Retrieval Conference (TREC-9), NIST Special Publication 2000, p. 673 
  7. Dufour N., A database for computerized multi-word unit recognition, In: Proc. ISP-3, Stuttgart 1998 
  8. Hajič J., Kodas – a simple method of natural language interface to a database, Explizite Beschreibung der Sprache und automatiche Textbearbeitung 6 (1984), Charles University, Prague (1984) 
  9. Hajič J., Nalcom: A multilevel nl-interface, Explizite Beschreibung der Sprache und automatiche Textbearbeitung 15 (1988), Charles University, Prague (1988) 
  10. Hajičová E., Borota J., Hajič J., Hnáková M., Kuboň V., Oliva, K., Panevová J., Text-and-inference based approach to question answering, Theoret. Comput. Linguistic 3 (1995) (1995) 
  11. Hirschman L., Gaizauskas R., Natural language question answering: The view from here, Natur. Language Engrg. 7 (2001), 275–300 
  12. Jirků P., Hajič J., Inferencing and search for an answer in tibaq, In: Proc. Ninth Internat. Conference on Computational Linguistics (E. Hajičová, ed.), Charles University, Prague 1982 
  13. Katz B., From sentence processing to information access on the world wide web, In: Proc. AAAI Spring Symposium on Natural Language, Processing for the World Wide Web, Stanford Univesity, Stanford 1997 
  14. Klaas S., Parsing Schemata: A Framework for Specification and Analysis of Parsing Algorithm, Springer–Verlag, Berlin 1996 
  15. Matoušek V., Simplified processing of elliptic and anaphoric utterances in a train timetable information retrieval dialogue system, In: Proc. Third Internat. Conference TSD 2000 (P. Sojka, I. Kopeček, and K. Pala, eds., Lecture Notes in Computer Science 1902), Springer–Verlag, Berlin 2001, p. 0399 (1902) 
  16. Maynard D., Cunningham H., Bontcheva, K., Dimitrov M., Adapting a robust multi-genre NE system for automatic content extraction, In: 10th Internat. Conference, AIMSA 2002, Varna (Lecture Notes in Artificial Intelligence 2443), Springer–Verlag, Berlin 2002, pp. 264–273 Zbl1020.68801
  17. Milward D., Thomas J., From information retrieval to information extraction, In: ACL 2000 Workshop on Recent Advances in Natural Language Processing and Information Retrieval 2000 
  18. Moldavan D., Harabagiu S., Pasca M., Mihalcea R., Goodrum R., Girji, R., Rus V., Lasso: A tool for surfing the answer net, In: Proc. Eight Text Retrieval Conference (TREC-8), NIST Special Publication 1999 
  19. Mouček R., Taušer K., Dialogue system for city for city information centre, In: Proc. 6th World MultConference on Systemics, Cybernetics and Informatics SCI 2002, Orlando 2001, pp. 536–567 
  20. Prager J., Browni E., One search engine or two for question-answering, In: Proc. Ninth Text Retrieval Conference (TREC-9), NIST Special Publication 2000, p. 235 
  21. Sgall P., Natural language understanding and the perspectives of question answeing, In: Proc. Ninth Internat. Conference on Computational Linguistics (E. Hajičová, ed.), Charles University, Prague 1982 
  22. Scott S., Gaizauskas R., University of sheffield trec-9 q&a system, In: Proc. Ninth Text Retrieval Conference (TREC-9), NIST Special Publication 2000 
  23. Sedláček R., Smrž P., A new Czech morphological analyser ajka, In: Proc. Fourth Internat. Conference TSD 2001 (P. Sojka, I. Kopeček, and K. Pala, eds., Lecture Notes in Computer Science 2166), Springer–Verlag, Berlin 2001, pp. 100–107 Zbl1009.68670
  24. Sriharii R., Li W., Information extraction supported question answering, In: Proc. Eight Text Retrieval Conference (TREC-8), NIST Special Publication 1999 
  25. Svoboda L., UIO, a dialog system for question answering, In: Proc. Znalosti 2003 Workshop (V. Svátek, ed.), 2003 
  26. Tomita M., Efficient Parsing for Natural Language, Kluwer, Dordrecht 1986 
  27. Zhang D., Lee W. S., A web-based question answering system, In: Proc. SMA Annual Symposium 2003, NUS, Singapore 2003 
  28. Žačková E., Partial Parsing for Czech, Ph.D. Thesis, Masaryk University, 2002 
  29. Žáčková E., Nepil, M., Popelínský L., Automatic tagging of compound verb groups in Czech corpora, In: Text, Speech and Dialogue: Proc. TSD’2000 Workshop (P. Sojka, I. Kopeček, and K. Pala, eds., Lecture Notes in Computer Science 1902), Springer–Verlag, Berlin 2000, p. 0115 (1902) 

NotesEmbed ?

top

You must be logged in to post comments.

To embed these notes on your page include the following JavaScript code on your page where you want the notes to appear.

Only the controls for the widget will be shown in your chosen language. Notes will be shown in their authored language.

Tells the widget how many notes to show per page. You can cycle through additional notes using the next and previous controls.

    
                

                
Note: Best practice suggests putting the JavaScript code just before the closing </body> tag.