Incident-Driven Machine Translation and Name Tagging for Low-resource Languages

Incident-Driven Machine Translation and Name Tagging for Low-resource Languages

We describe novel approaches to tackling the problem of natural language processing for low-resource languages. The approaches are embodied in systems for name tagging and machine translation (MT) that we constructed to participate in the NIST LoReHLT evaluation in 2016. Our methods include universa...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Machine translation 2018-06, Vol.32 (1/2), p.59-89
Hauptverfasser: Hermjakob, Ulf, Li, Qiang, Marcu, Daniel, May, Jonathan, Mielke, Sebastian J., Pourdamghani, Nima, Pust, Michael, Shi, Xing, Knight, Kevin, Levinboim, Tomer, Murray, Kenton, Chiang, David, Zhang, Boliang, Pan, Xiaoman, Di Lu, Lin, Ying, Ji, Heng
Format: Artikel
Sprache:eng
Schlagworte:
Artificial Intelligence
Computational Linguistics
Computer Science
Knowledge acquisition
Machine translation
Marking
Natural language processing
Natural Language Processing (NLP)
Translation methods and strategies
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We describe novel approaches to tackling the problem of natural language processing for low-resource languages. The approaches are embodied in systems for name tagging and machine translation (MT) that we constructed to participate in the NIST LoReHLT evaluation in 2016. Our methods include universal tools, rapid resource and knowledge acquisition, rapid language projection, and joint methods for MT and name tagging.
ISSN:0922-6567
1573-0573
DOI:10.1007/s10590-017-9207-1