MT output | Sciweavers

14

LREC
2008

111views Education» more LREC 2008»

Sensitivity of Automated MT Evaluation Metrics on Higher Quality MT Output: BLEU vs Task-Based Evaluation Methods

13 years 6 months ago

We report the results of an experiment to assess the ability of automated MT evaluation metrics to remain sensitive to variations in MT quality as the average quality of the compa...

Bogdan Babych, Anthony Hartley

claim paper

Read More »

15

click to vote

ACL
2008

158views Computational Linguistics» more ACL 2008»

Combining Source and Target Language Information for Name Tagging of Machine Translation Output

13 years 6 months ago

Download www.aclweb.org

A Named Entity Recognizer (NER) generally has worse performance on machine translated text, because of the poor syntax of the MT output and other errors in the translation. As som...

Shasha Liao

claim paper

Read More »

19

click to vote

AMTA
2004
Springer

254views Information Technology» more AMTA 2004»

A Fluency Error Categorization Scheme to Guide Automated Machine Translation Evaluation

13 years 10 months ago

Download www.comp.leeds.ac.uk

Abstract. Existing automated MT evaluation methods often require expert human translations. These are produced for every language pair evaluated and, due to this expense, subsequen...

Debbie Elliott, Anthony Hartley, Eric Atwell

claim paper

Read More »

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers