The CLIN27 Shared Task: Translating Historical Text to Contemporary Language for Improving Automatic Linguistic Annotation

The CLIN27 shared task evaluates the effect of translating historical text to modern text with the goal of improving the quality of the output of contemporary natural language processing tools applied to the text. We focus on improving part-of-speech tagging analysis of seventeenth-century Dutch. Eight teams took part in the shared task. The best results were obtained by teams employing character-based machine translation. The best system obtained an error reduction of 51% in comparison with the baseline of tagging unmodified text. This is close to the error reduction obtained by human transla... Mehr ...

Volltext
Verfasser: Tjong Kim Sang, Erik
Bollman, Marcel
Boschker, Remko
Casacuberta, Francisco
Dietz, F.M.
Dipper, Stefanie
Domingo, Miguel
van der Goot, Rob
van Koppen, J.M.
Ljubešić, Nikola
Östling, Robert
Petran, Florian
Pettersson, Eva
Scherrer, Yves
Schraagen, M.P.
Sevens, Leen
Tiedeman, Jörg
Vanallemeersch, Tom
Zervanou, K.
Dokumenttyp: Artikel
Erscheinungsdatum: 2017
Schlagwörter: historical text / text normalization / neural networks / machine translation / dutch language
Sprache: Englisch
Permalink: https://search.fid-benelux.de/Record/base-29454855
Datenquelle: BASE; Originalkatalog
Powered By: BASE
Link(s) : https://dspace.library.uu.nl/handle/1874/360876

The CLIN27 shared task evaluates the effect of translating historical text to modern text with the goal of improving the quality of the output of contemporary natural language processing tools applied to the text. We focus on improving part-of-speech tagging analysis of seventeenth-century Dutch. Eight teams took part in the shared task. The best results were obtained by teams employing character-based machine translation. The best system obtained an error reduction of 51% in comparison with the baseline of tagging unmodified text. This is close to the error reduction obtained by human translation (57%).