POPELÍNSKÝ, Lubomír. Strojové učení a přirozený jazyk (abtrakt tutoriálu) (Machine learning and natural language processing). In Sborník konference ZNALOSTI 2003. Ostrava: FEI VŠB-TU Ostrava, 2003, p. 18-19. ISBN 80-248-0229-5.
Other formats:   BibTeX LaTeX RIS
Basic information
Original name Strojové učení a přirozený jazyk (abtrakt tutoriálu)
Name (in English) Machine learning and natural language processing
Authors POPELÍNSKÝ, Lubomír (203 Czech Republic, guarantor).
Edition Ostrava, Sborník konference ZNALOSTI 2003, p. 18-19, 2 pp. 2003.
Publisher FEI VŠB-TU Ostrava
Other information
Original language Czech
Type of outcome Proceedings paper
Field of Study 10201 Computer sciences, information science, bioinformatics
Country of publisher Czech Republic
Confidentiality degree is not subject to a state or trade secret
RIV identification code RIV/00216224:14330/03:00009163
Organization unit Faculty of Informatics
ISBN 80-248-0229-5
Keywords in English machine learning; natural language processing
Tags machine learning, natural language processing
Changed by Changed by: doc. RNDr. Lubomír Popelínský, Ph.D., učo 1945. Changed: 21/11/2003 10:02.
Abstract
Natural language processing (NLP) aims at employing computers for natural language understanding. We focus here on application machine learning in NLP, namely on instance-based learning, Bayesian methods, transformation-based learning and inductive logic programming. Different disambiguation tasks will be discussed including morphological disambiguation and word-sense disambiguation. In the second part we will introduce application of learning for document categorization and information extraction from collection of documents. We conclude with text mining. We will present the results obtained with NLP and machine learning in NLP Lab FI MU.
Abstract (in English)
Natural language processing (NLP) aims at employing computers for natural language understanding. We focus here on application machine learning in NLP, namely on instance-based learning, Bayesian methods, transformation-based learning and inductive logic programming. Different disambiguation tasks will be discussed including morphological disambiguation and word-sense disambiguation. In the second part we will introduce application of learning for document categorization and information extraction from collection of documents. We conclude with text mining. We will present the results obtained with NLP and machine learning in NLP Lab FI MU.
Links
MSM 143300003, plan (intention)Name: Interakce člověka s počítačem, dialogové systémy a asistivní technologie
Investor: Ministry of Education, Youth and Sports of the CR, Human-computer interaction, dialog systems and assistive technologies
PrintDisplayed: 8/5/2024 04:09