A4 Vertaisarvioitu artikkeli konferenssijulkaisussa
Sentence Compression for Automatic Subtitling
Tekijät: Juhani Luotolahti, Filip Ginter
Toimittaja: Beäta Megyesi
Konferenssin vakiintunut nimi: Nordic Conference on Computational Linguistics
Julkaisuvuosi: 2015
Kokoomateoksen nimi: Proceedings of NoDaLiDa 2015
Aloitussivu: 134
Lopetussivu: 143
Sivujen määrä: 10
ISBN: 978-91-7519-098-3
Verkko-osoite: https://aclweb.org/anthology/W/W15/W15-1818.pdf
This paper investigates sentence compression for automatic subtitle generation using supervised machine learning. We present a method for sentence compression as well as discuss generation of training data from compressed Finnish sentences, and different approaches to the problem. The method we present outperforms state-of-the-art baseline in both automatic and human valuation. On real data, 44.9% of the sentences produced by the compression algorithm have been judged to be useable as-is or after minor edits.
Ladattava julkaisu This is an electronic reprint of the original article. |