Year: 2019
Type: conference-paper
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.
DOI: 10.18653/v1/d19-6506
Authors: Yves Scherrer, Jörg Tiedemann, Sharid Loáiciga
Institutions: University of Helsinki, University of Gothenburg
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
OpenAlex ID: W2989066524