Does natural selection apply to natural language processing? An experiment for multiword unit extraction

Proceedings of the IEEE International Conference on Systems, Man and Cybernetics

Volumn 1, Issue , 2001, Pages 205-212

  Dias, Gaël ^a   Nunes, Sérgio ^a  

^a UNIVERSITY OF BEIRA INTERIOR   (Portugal)

Author keywords

Genetic algorithms; Multiword unit extraction; Similarity measures

Indexed keywords

COMPUTER AIDED LANGUAGE TRANSLATION; DIGITAL ARITHMETIC; GENETIC ALGORITHMS; HEURISTIC PROGRAMMING; INFORMATION RETRIEVAL SYSTEMS; OPTIMIZATION; PROBABILITY;

GENETIC ALGORITHM FOR THE EXTRACTION OF MULTIWORD UNITS; MULTIWORD UNIT EXTRACTION; SIMILARITY MEASURES;

NATURAL LANGUAGE PROCESSING SYSTEMS;

EID: 0035723669     PISSN: 08843627     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (24)

1. What can be learned from raw texts? An integrated tool for the acquisition of case rules, taxonomic relations and disambiguation criteria
2. The balancing act combining symbolic and statistical approaches to language
3. Identifying and integrating terminologically relevant multiword units in the IJS-ELAN slovene-english parallel corpus
4. Normalisation of association measures for multiword lexical unit extraction
5. Accurate methods for the statistics of surprise and coincidence
6. Concept management in text via natural language processing: The CLARIT approach
7. A pattern matching method for finding noun and proper noun translations
8. A hybrid approach to term recognition
9. Extracting nested collocations
10. Concordances for parallel texts
11. Noms composés, termes, dénominations complexes: Problématiques linguistiques et traitements automatiques
12. La pratique des segments répétés
13. The relevance of frequency lists for error correction and robust lemmatization
14. Using localMaxs algorithm for the extraction of contiguous and non-contiguous multiword lexical units
15. Retrieving collocations from text: XTRACT
16. Translating collocations for bilingual lexicons: A statistical approach