Year: 1999
Type: conference-paper
Abstract: We present a general architecture for efficient and deterministic morphological analysis based on memory-based learning, and apply it to morphological analysis of Dutch.The system makes direct mappings from letters in context to rich categories that encode morphological boundaries, syntactic class labels, and spelling changes.Both precision and recall of labeled morphemes are over 84% on held-out dictionary test words and estimated to be over 93% in free text.
Authors: Antal van den Bosch, Walter Daelemans
Institution: Tilburg University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W2105378193
