Converting morphological information using lexicalized and general conversion

DOI10.1007/3-540-44686-9_32MaRDI QIDQ2763147zbMATH OpenFDO

Authors Mitsuo Shimohata, Eiichiro Sumita

Publication date 14 January 2002

Published in Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL http://link.springer.de/link/service/series/0558/bibs/2004/20040319

Mathematics Subject Classification ID

Natural language processing (68T50) Computing methodologies and applications (68U99)

Review text

Today, many kinds of tagged corpora are available for research use. Often a different morphological system is used in each corpus. This makes it difficult to merge different types of morphological information, since conversion between different systems is complex and necessitates a understanding of both systems. This paper describes a method of converting morphological information between two different systems by using lexicalized and general conversion. The difference between lexicalized and general conversion is the existence or absence of a lexicalized condition. Which conversion is applied depends on the frequency of segments. For the entire collection see [Zbl 0976.68583].

Recommendations

• scientific article; zbMATH DE number 5370220
• The morphological analysis using the phonetic alternations
• Morphological categorization using attribute value trees and XML
• An account of the challenge of tagging a reference corpus for Brazilian Portuguese
• Treatment of unknown words

Cited in

(1)

• Zone morphological processing of texts in natural languages

This page was built for publication: Converting morphological information using lexicalized and general conversion

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2763147)