Scherrer , Y , Tiedemann , J & Loáiciga , S 2019 , Analysing concatenation approaches to document-level NMT in two different domains . in The Fourth Workshop on Discourse in Machine Translation : Proceedings of the Workshop . The Association for Computational Linguistics , Stroudsburg , pp. 51-61 , Workshop on Discourse in Machine Translation , Hong Kong , China , 03/11/2019 . https://doi.org/10.18653/v1/D19-6506
Titel: | Analysing concatenation approaches to document-level NMT in two different domains |
Författare: | Scherrer, Yves; Tiedemann, Jörg; Loáiciga, Sharid |
Upphovmannens organisation: | Department of Digital Humanities Language Technology Mind and Matter |
Utgivare: | The Association for Computational Linguistics |
Datum: | 2019-11-01 |
Språk: | eng |
Sidantal: | 11 |
Tillhör serie: | The Fourth Workshop on Discourse in Machine Translation |
ISBN: | 978-1-950737-74-1 |
DOI: | https://doi.org/10.18653/v1/D19-6506 |
Permanenta länken (URI): | http://hdl.handle.net/10138/306876 |
Abstrakt: | In this paper, we investigate how different aspects of discourse context affect the performance of recent neural MT systems. We describe two popular datasets covering news and movie subtitles and we provide a thorough analysis of the distribution of various document-level features in their domains. Furthermore, we train a set of context-aware MT models on both datasets and propose a comparative evaluation scheme that contrasts coherent context with artificially scrambled documents and absent context, arguing that the impact of discourse-aware MT models will become visible in this way. Our results show that the models are indeed affected by the manipulation of the test data, providing a different view on document-level translation quality than absolute sentence-level scores. |
Subject: |
113 Computer and information sciences
6121 Languages |
Referentgranskad: | Ja |
Licens: | cc_by |
Användningsbegränsning: | openAccess |
Parallelpublicerad version: | publishedVersion |
Finansierad av: | European Commission / Horizon 2020 European Commission |
Finansierings ID: |
771113 |
Totalt antal nerladdningar: Laddar...
Filer | Storlek | Format | Granska |
---|---|---|---|
D19_6506.pdf | 259.2Kb | Granska/Öppna |