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

• Main Authors: Wiechetek, Linda, Argese, Chiara, Pirinen, Tommi, Trosterud, Trond
• Format: Article in Journal/Newspaper
• Language: English
• Published: CEUR-WS 2020
• Subjects: VDP::Humanities: 000::Linguistics: 010::Sami language: 031; VDP::Humaniora: 000::Språkvitenskapelige fag: 010::Samisk språk: 031; North Sámi; sami; Sámi; samisk
• Online Access: https://hdl.handle.net/10037/20151

Source at http://ceur-ws.org/Vol-2769/paper_49.pdf . CEUR Workshop Proceedings home page at http://ceur-ws.org/Vol-2769/ . 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 .