Enforcing Consistent Translation of German Compound Coreferences
- Coreferences to a German compound (e.g. Nordwand) can be made using its last constituent (e.g. Wand). Intuitively, both coreferences and the last constituent of the compound should share the same translation. However, since Statistical Machine Translation (SMT) systems translate at sentence level, they both may be translated inconsistently across the document. Several studies focus on document level consistency, but mostly in general terms. This paper presents a method to enforce consistency in this particular case. Using two in-domain phrase-based SMT systems, we analyse the effects of compound coreference translation consistency on translation quality and readability of documents. Experimental results show that our method improves correctness and consistency of those coreferences as well as document readability.
Download full text files
Main Conference Proceedings of the 12th Konvens 2014
Additional Services
| Author: | Laura Mascarell, Mark Fishel, Natalia Korchagina, Martin Volk |
|---|---|
| URN: | https://nbn-resolving.org/urn:nbn:de:gbv:hil2-opus-2684 |
| Parent Title (English): | Proceedings of the 12th edition of the KONVENS conference |
| Document Type: | Conference Proceeding |
| Language: | English |
| Date of Publication (online): | 2014/10/22 |
| Release Date: | 2014/10/22 |
| Tag: | Multilinguale Systeme machine translation; multilingual systems |
| GND Keyword: | Maschinelle Übersetzung |
| First Page: | 58 |
| Last Page: | 65 |
| PPN: | Link zum Katalog |
| Institutes: | Fachbereich III / Informationswissenschaft und Sprachtechnologie |
| DDC classes: | 400 Sprache / 400 Sprache, Linguistik |
| Collections: | KONVENS 2014 / Proceedings of the 12th KONVENS 2014 |
| Licence (German): |  Creative Commons - Namensnennung 3.0 |
