Memory-based lexical acquisition and processing

Walter Daelemans


Abstract
Current approaches to computational lexicology in language technology are knowledge-based (competence-oriented) and try to abstract away from specific formalisms, domains, and applications. This results in severe complexity, acquisition and reusability bottlenecks. As an alternative, we propose a particular performance-oriented approach to Natural Language Processing based on automatic memory-based learning of linguistic (lexical) tasks. The consequences of the approach for computational lexicology are discussed, and the application of the approach on a number of lexical acquisition and disambiguation tasks in phonology, morphology and syntax is described.
Anthology ID:
1993.eamt-1.6
Volume:
Third International EAMT Workshop: Machine Translation and the Lexicon
Month:
April 26–28
Year:
1993
Address:
Heidelberg, Germany
Editors:
Robert E. Frederking, Kathryn B. Taylor
Venue:
EAMT
SIG:
Publisher:
Springer Berlin Heidelberg
Note:
Pages:
85–98
Language:
URL:
https://aclanthology.org/1993.eamt-1.6
DOI:
Bibkey:
Cite (ACL):
Walter Daelemans. 1993. Memory-based lexical acquisition and processing. In Third International EAMT Workshop: Machine Translation and the Lexicon, pages 85–98, Heidelberg, Germany. Springer Berlin Heidelberg.
Cite (Informal):
Memory-based lexical acquisition and processing (Daelemans, EAMT 1993)
Copy Citation: