
An Analysis of Comment-Revision Thresholds in Bilingual Electronic Meetings
Author(s) -
Bart Garner,
Milam Aiken
Publication year - 2016
Publication title -
international journal of computer and technology
Language(s) - English
Resource type - Journals
ISSN - 2277-3061
DOI - 10.24297/ijct.v15i10.4379
Subject(s) - comprehension , point (geometry) , computer science , similarity (geometry) , minor (academic) , affect (linguistics) , natural language processing , contrast (vision) , artificial intelligence , linguistics , psychology , mathematics , communication , political science , philosophy , geometry , image (mathematics) , programming language , law
Prior studies have shown that providing participants in bilingual or multilingual, electronic meetings with the capability of revising comments can increase the accuracy of translations to other languages. This is often done via a round-trip translation (RTT) in which the source text is translated to another language, translated back again, and compared with the original. If the similarity falls below a certain threshold, e.g. 50%, the originator may wish to revise the comment before final submission. However, minor changes might not be needed, and it is not clear where the threshold lies between acceptable and non-acceptable text. In this study, we seek to determine at what point accuracy can be improved by comment revision. Results show that the threshold did not affect the target-language comprehension, but higher thresholds substantially increased the cognitive burden for users in the form of alerts and comment revisions.