Leveraging rule-based machine translation knowledge for under-resourced neural machine translation models
View/ Open
Date
2019-08-19Author
Torregrosa, Daniel
Pasricha, Nivranshu
Chakravarth, Bharathi Raja
Masoud, Maraim
Alonso, Juan
Casas, Noe
Arcan, Mihael
Metadata
Show full item recordUsage
This item's downloads: 354 (view details)
Recommended Citation
Torregrosa, Daniel , Pasricha, Nivranshu, Chakravarth, Bharathi Raja, Masoud, Maraim , Alonso, Juan , Casas, Noe , & Arcan, Mihael (2019). Leveraging rule-based machine translation knowledge for under-resourced neural machine translation models. Paper presented at the Machine Translation Summit, Dublin, Ireland, 19-23 August, doi:10.13025/prgj-bk28
Published Version
Abstract
Rule-based machine translation is a machine translation paradigm where linguistic
knowledge is encoded by an expert in the
form of rules that translate from source to
target language. While this approach grants
total control over the output of the system,
the cost of formalising the needed linguistic knowledge is much higher than training
a corpus-based system, where a machine
learning approach is used to automatically
learn to translate from examples. In this
paper, we describe different approaches to
leverage the information contained in rulebased machine translation systems to improve a corpus-based one, namely, a neural
machine translation model, with a focus on
a low-resource scenario. Our results suggest that adding morphological information
to the source language is as effective as using subword units in this particular setting.