Comparative Quality Estimation for Machine Translation Observations on Machine Learning and Features
A deeper analysis on Comparative Quality Estimation is presented by extending the state-of-the-art methods with adequacy and grammatical features from other Quality Estimation tasks. The previously used linear method, unable to cope with the augmented features, is replaced with a boosting classifier...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sciendo
2017-06-01
|
| Series: | Prague Bulletin of Mathematical Linguistics |
| Online Access: | https://doi.org/10.1515/pralin-2017-0029 |
| id |
doaj-9b26244c00534c209dfa6ab7c4c191b0 |
|---|---|
| record_format |
Article |
| spelling |
doaj-9b26244c00534c209dfa6ab7c4c191b02021-09-05T13:59:53ZengSciendoPrague Bulletin of Mathematical Linguistics 1804-04622017-06-01108130731810.1515/pralin-2017-0029pralin-2017-0029Comparative Quality Estimation for Machine Translation Observations on Machine Learning and FeaturesAvramidis Eleftherios0German Research Center for Artificial Intelligence (DFKI Berlin), Language Technology LabA deeper analysis on Comparative Quality Estimation is presented by extending the state-of-the-art methods with adequacy and grammatical features from other Quality Estimation tasks. The previously used linear method, unable to cope with the augmented features, is replaced with a boosting classifier assisted by feature selection. The methods indicated show improved performance for 6 language pairs, when applied on the output from MT systems developed over 7 years. The improved models compete better with reference-aware metrics.https://doi.org/10.1515/pralin-2017-0029 |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Avramidis Eleftherios |
| spellingShingle |
Avramidis Eleftherios Comparative Quality Estimation for Machine Translation Observations on Machine Learning and Features Prague Bulletin of Mathematical Linguistics |
| author_facet |
Avramidis Eleftherios |
| author_sort |
Avramidis Eleftherios |
| title |
Comparative Quality Estimation for Machine Translation Observations on Machine Learning and Features |
| title_short |
Comparative Quality Estimation for Machine Translation Observations on Machine Learning and Features |
| title_full |
Comparative Quality Estimation for Machine Translation Observations on Machine Learning and Features |
| title_fullStr |
Comparative Quality Estimation for Machine Translation Observations on Machine Learning and Features |
| title_full_unstemmed |
Comparative Quality Estimation for Machine Translation Observations on Machine Learning and Features |
| title_sort |
comparative quality estimation for machine translation observations on machine learning and features |
| publisher |
Sciendo |
| series |
Prague Bulletin of Mathematical Linguistics |
| issn |
1804-0462 |
| publishDate |
2017-06-01 |
| description |
A deeper analysis on Comparative Quality Estimation is presented by extending the state-of-the-art methods with adequacy and grammatical features from other Quality Estimation tasks. The previously used linear method, unable to cope with the augmented features, is replaced with a boosting classifier assisted by feature selection. The methods indicated show improved performance for 6 language pairs, when applied on the output from MT systems developed over 7 years. The improved models compete better with reference-aware metrics. |
| url |
https://doi.org/10.1515/pralin-2017-0029 |
| work_keys_str_mv |
AT avramidiseleftherios comparativequalityestimationformachinetranslationobservationsonmachinelearningandfeatures |
| _version_ |
1717812838031949824 |