Issue #9 – Domain Adaptation for Neural MT

13 Sep18

Author: Raj Nath Patel, Machine Translation Scientist @ Iconic

While Neural MT has raised the bar in terms of the quality of general purpose machine translation, it is still limited when it comes to more intricate or technical use cases. That is where domain adaptation — the process of developing and adapting MT for specific industries, content types, and use cases — has a big part to play.

In this post, we take a look at some of the commonly used techniques for domain adaptation of Neural Machine Translation and summarise the survey of Chu and Wang (2017) who covered this topic in great detail.

There are many studies of domain adaptation for Neural MT, which can be mainly divided into two categories: data centric and model centric. The data centric category focuses on the data being used rather than specialized models for the required domain. The data used can be either in-domain monolingual corpora, synthetic corpora, or parallel corpora. On the other hand, the model centric category focuses on Neural MT models that are specialized for domain adaptation, which can be either the training objective,
To finish reading, please visit source site