Analysing concatenation approaches to document-level NMT in two different domains

Show full item record



Permalink

http://hdl.handle.net/10138/306876

Citation

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

Title: Analysing concatenation approaches to document-level NMT in two different domains
Author: Scherrer, Yves; Tiedemann, Jörg; Loáiciga, Sharid
Contributor: University of Helsinki, Department of Digital Humanities
University of Helsinki, Department of Digital Humanities
Publisher: The Association for Computational Linguistics
Date: 2019-11-01
Language: eng
Number of pages: 11
Belongs to series: The Fourth Workshop on Discourse in Machine Translation Proceedings of the Workshop
ISBN: 978-1-950737-74-1
URI: http://hdl.handle.net/10138/306876
Abstract: 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
Rights:


Files in this item

Total number of downloads: Loading...

Files Size Format View
D19_6506.pdf 259.2Kb PDF View/Open

This item appears in the following Collection(s)

Show full item record