Samenvatting
We compare three approaches to statistical machine translation (pure phrase-based, fac-
tored phrase-based and neural) by performing a fine-grained manual evaluation via error an-
notation of the systems’ outputs. The error types in our annotation are compliant with the
multidimensional quality metrics (MQM), and the annotation is performed by two annotators.
Inter-annotator agreement is high for such a task, and results show that the best performing
system (neural) reduces the errors produced by the worst system (phrase-based) by 54%.
tored phrase-based and neural) by performing a fine-grained manual evaluation via error an-
notation of the systems’ outputs. The error types in our annotation are compliant with the
multidimensional quality metrics (MQM), and the annotation is performed by two annotators.
Inter-annotator agreement is high for such a task, and results show that the best performing
system (neural) reduces the errors produced by the worst system (phrase-based) by 54%.
| Originele taal-2 | English |
|---|---|
| Pagina's (van-tot) | 121-132 |
| Aantal pagina's | 12 |
| Tijdschrift | The Prague Bulletin of Mathematical Linguistics |
| Volume | 108 |
| Nummer van het tijdschrift | 1 |
| DOI's | |
| Status | Published - 2017 |