Suoidne-varra-bleahkka-mála-bihkka-senet-dielku 'hay-blood-ink-paint-tar-mustard-stain' -Should compounds be lexicalized in NLP?

Permanent link
https://hdl.handle.net/10037/20151
Thumbnail
View/Open
Published version (PDF)
Date
2020-12-11
Type
Journal article
Tidsskriftartikkel

Author
Wiechetek, Linda; Argese, Chiara; Pirinen, Tommi; Trosterud, Trond
Abstract
Lexicalizing compounds, in addition to treating them dynamically, is a key element in giving us idiomatic translations and detecting compound errors. We present and evaluate an e-dictionary (NDS) and a grammar checker (GramDivvun) for North Sámi. We achieve a coverage of 98% for NDSqueries and of 96% for compound error detection in GramDivvun.
Description
Source at http://ceur-ws.org/Vol-2769/paper_49.pdf. CEUR Workshop Proceedings home page at http://ceur-ws.org/Vol-2769/.
Publisher
CEUR-WS
Citation
Wiechetek, Argese, Pirinen, Trosterud. Suoidne-varra-bleahkka-mála-bihkka-senet-dielku 'hay-blood-ink-paint-tar-mustard-stain' -Should compounds be lexicalized in NLP?. CEUR Workshop Proceedings. 2020
Metadata
Show full item record
Collections
Copyright 2020 The Author(s)