Neural and Statistical Methods for Leveraging Meta-information in Machine Translation
This work addresses the challenge of enhancing translation accuracy for specific text categories, though it is incremental as it applies existing neural methods to a known framework.
The paper tackles the problem of improving machine translation quality by leveraging meta-information, such as text category, within a statistical machine translation framework, resulting in translation quality improvements of up to 3% BLEU score in some categories.
In this paper, we discuss different methods which use meta information and richer context that may accompany source language input to improve machine translation quality. We focus on category information of input text as meta information, but the proposed methods can be extended to all textual and non-textual meta information that might be available for the input text or automatically predicted using the text content. The main novelty of this work is to use state-of-the-art neural network methods to tackle this problem within a statistical machine translation (SMT) framework. We observe translation quality improvements up to 3% in terms of BLEU score in some text categories.