Informace o publikaci

Evaluating the State-of-the-Art Sentence Alignment System on Literary Texts

Logo poskytovatele
Autoři

SIGNORONI Edoardo

Rok publikování 2021
Druh Článek ve sborníku
Konference Recent Advances in Slavonic Natural Language Processing (RASLAN 2021)
Fakulta / Pracoviště MU

Fakulta informatiky

Citace
www
Klíčová slova Parallel corpora; Automatic alignment; Literary text
Popis Sentence alignment is a useful task with many applications in Natural Language Processing and Digital Humanities. This paper presents an evaluation of Vecalign, the state-of-the-art method for automatic sen- tence alignment, on two bilingual corpora built from literary texts. This preliminary study shows that Vecalign performs well for literary texts and gives insights on its remaining issues through a qualitative evaluation of the output alignments.
Související projekty:

Používáte starou verzi internetového prohlížeče. Doporučujeme aktualizovat Váš prohlížeč na nejnovější verzi.

Další info