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

Investor logo

Warning

This publication doesn't include Faculty of Arts. It includes Faculty of Informatics. Official publication website can be found on muni.cz.
Authors

SIGNORONI Edoardo

Year of publication 2021
Type Article in Proceedings
Conference Recent Advances in Slavonic Natural Language Processing (RASLAN 2021)
MU Faculty or unit

Faculty of Informatics

Citation
Web
Keywords Parallel corpora; Automatic alignment; Literary text
Description 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.
Related projects:

You are running an old browser version. We recommend updating your browser to its latest version.