Login (DCU Staff Only)
Login (DCU Staff Only)

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

Automatic error classification with multiple error labels

Popović, Maja orcid logoORCID: 0000-0001-8234-8745 and Vilar, David (2019) Automatic error classification with multiple error labels. In: MT Summit XVII, 19 - 23 Aug 2019, Dublin, Ireland.

Abstract
Although automatic classification of machine translation errors still cannot provide the same detailed granularity as manual error classification, it is an important task which enables estimation of translation errors and better understanding of the analysed MT system, in a short time and on a large scale. State-of-the-art methods use hard decisions to assign single error labels to each word. This work presents first results of a new error classification method, which assigns multiple error labels to each word. We assign fractional counts for each label, which can be interpreted as a confidence for the label. Our method generates sensible multi-error suggestions, and improves the correlation between manual and automatic error distributions.
Metadata
Item Type:Conference or Workshop Item (Paper)
Event Type:Conference
Refereed:Yes
Subjects:Computer Science > Computational linguistics
Computer Science > Machine translating
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Research Initiatives and Centres > ADAPT
Published in: Proceedings of Machine Translation Summit XVII: Research Track. 1. European Association for Machine Translation.
Publisher:European Association for Machine Translation
Official URL:https://www.aclweb.org/anthology/W19-6609
Copyright Information:© 2019 The Authors. CC-BY-ND 4.0
Funders:Science Foundation Ireland (Grant 13/RC/2106), European Regional Development Fund
ID Code:24591
Deposited On:10 Jun 2020 13:13 by Maja Popovic . Last Modified 05 Jan 2021 12:11
Documents

Full text available as:

[thumbnail of WER_Error_Classification.pdf]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
159kB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record