A preliminary evaluation of metadata records machine translation

Description:

Article discussing a preliminary evaluation study of metadata records machine translation. This study evaluates freely available machine translation (MT) services' performance in translating metadata records.

Creator(s):
Creation Date: 2012
Partner(s):
UNT College of Information
Collection(s):
UNT Scholarly Works
Usage:
Total Uses: 120
Past 30 days: 7
Yesterday: 0
Creator (Author):
Chen, Jiangping

University of North Texas

Creator (Author):
Ding, Ren

Wuhan University

Creator (Author):
Jiang, Shan

Chinese Academy of Sciences

Creator (Author):
Knudson, Ryan

University of North Texas

Publisher Info:
Publisher Name: Emerald Group Publishing
Place of Publication: [Bingley, United Kingdom]
Date(s):
  • Creation: 2012
Description:

Article discussing a preliminary evaluation study of metadata records machine translation. This study evaluates freely available machine translation (MT) services' performance in translating metadata records.

Degree:
Note:

This is the preprint version of an article published in Electronic Library. This article is © Emerald Group Publishing and permission has been granted for this version to appear here. Emerald does not grant permission for this article to be further copied/distributed or hosted elsewhere without the express permission from Emerald Group Publishing Limited.

Note:

Abstract: Purpose: The purpose of this study is to evaluate freely available machine translation (MT) services' performance in translating metadata records. Design/methodology/approach: Randomly selected metadata records were translated from English to Chinese using Google, Bing, and SYSTRAN MT systems. These translations were then evaluated using a five point scale for both fluency and adequacy. Missing count (words not translated) and incorrect count (words incorrectly translated) were also recorded. Findings: Concerning both fluency and adequacy, Google and Bing's translations of more than 70 percent of test data received scores equal to or greater than three, representative of "non-native Chinese" and "much coverage," respectively. SYSTRAN scored lowest in both measures. However, these differences were not statistically significant. A Pearson correlation analysis demonstrated a strong relationship (r=0.86) between fluency and adequacy. Missing count and incorrect count strongly correlated with fluency and adequacy. Originality/value: Most existing digital collections can be accessed in English alone. Few digital collections in the USA support multilingual information access (MLIA) that enables users of differing languagees to search, browse, recognize and use information in the collections. Human translation is one solution, but it is neither time nor cost effective for most libraries. This study serves as a first step to understand the performance of current MT systems and to design effective and efficient MLIA services for digital collections.

Physical Description:

15 p.

Language(s):
Subject(s):
Keyword(s): translations | metadata records | Systran | multilingual information access
Source: The Electronic Library, 2012, Bingley: Emerald Group Publishing, pp. 264-277
Partner:
UNT College of Information
Collection:
UNT Scholarly Works
Identifier:
  • DOI: 10.1108/02640471211221377 |
  • ARK: ark:/67531/metadc96821
Resource Type: Article
Format: Text
Rights:
Access: Public
Citation:
Publication Title: The Electronic Library
Volume: 30
Issue: 2
Page Start: 264
Page End: 277
Peer Reviewed: Yes