Aspects of Terminological and Named Entity Knowledge within Rule-Based Machine Translation Models for Under-Resourced Neural Machine Translation Scenarios
This work addresses the challenge of enhancing translation quality for under-resourced languages, but it is incremental as it builds on existing methods with limited new gains.
The paper tackled the problem of improving neural machine translation in low-resource scenarios by leveraging information from rule-based systems, but found that most approaches did not significantly alter automatic evaluation results, with only preliminary qualitative benefits like preserving passive voice in some cases.
Rule-based machine translation is a machine translation paradigm where linguistic knowledge is encoded by an expert in the form of rules that translate text from source to target language. While this approach grants extensive 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 rule-based machine translation systems to improve a corpus-based one, namely, a neural machine translation model, with a focus on a low-resource scenario. Three different kinds of information were used: morphological information, named entities and terminology. In addition to evaluating the general performance of the system, we systematically analysed the performance of the proposed approaches when dealing with the targeted phenomena. Our results suggest that the proposed models have limited ability to learn from external information, and most approaches do not significantly alter the results of the automatic evaluation, but our preliminary qualitative evaluation shows that in certain cases the hypothesis generated by our system exhibit favourable behaviour such as keeping the use of passive voice.