Translation Adequacy and Preference Evaluation Tool (TAP-ET)

Published

May 28, 2008

Author(s)

Mark A. Przybocki, Kay Peterson, P. S. Bronsart

Abstract

Evaluation of Machine Translation (MT) technology is often tied to the requirement for tedious manual judgments of translation quality. While automated MT metrology continues to be an active area of research, a well known and often accepted standard metric is the manual human assessment of adequacy and fluency. There are several software packages (RWTH, 2000) (LDC, 2005) that have been used to facilitate these judgments, but for the 2008 NIST Open MT Evaluation (NIST, 2008), NIST s Speech Group created an online software tool to accommodate the requirement for centralized data and distributed judges. This paper introduces the NIST TAP-ET application and reviews the reasoning underlying its design. Where available, analysis of data sets judged for Adequacy and Preference using the TAP-ET application will be presented. TAP-ET is freely available and ready to download, and contains a variety of customizable features.

Conference Dates

May 28-30, 2008

Conference Location

Marrekech

Conference Title

The sixth international conference on Language Resources and Evaluation, LREC 2008

Pub Type

Conferences

Download Paper

Local Download

Keywords

Machine Translation Evaluation, Evaluation Software, Human Assessments, Human Judgments, Adequacy, Preference

Citation

Przybocki, M. , Peterson, K. and Bronsart, P. (2008), Translation Adequacy and Preference Evaluation Tool (TAP-ET), The sixth international conference on Language Resources and Evaluation, LREC 2008, Marrekech, -1, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=152152 (Accessed December 11, 2024)