A Multi-agent solution for managing complexity in English to Sinhala machine translation

Abstract

Machine translation turns out to be an inherently complex process requiring serious attention to morphological, syntactic and semantic complexity within both the source and the target languages. Most of the existing approaches to machine translation (MT) circumvent the complexity with the assumption that morphological, syntactic and semantic analysis can be done independently and sequentially. This has resulted in depriving us of the opportunity to use the language complexity to generate high-quality translations. In view of this, research has been conducted to develop a multi-agent systems solution for MT that uses the language complexity as an opportunity for generating a more realistic translation from English to Sinhala. This multi-agent solution primarily comprises a six-agent swarm to deliberate on morphological, syntactic and semantic concerns of the source and the target languages without being constrained to operate in a sequential manner. These agents use the ontology of corpora and dictionary of two languages. This approach is inspired by the fact that people understand a sentence by incrementally reading through words while simultaneously considering the syntax and semantics. As such, when the system progresses in identification of words one by one, both syntactical and semantic concerns are entertained up to the current point of reading. As a result, initially decided words may be changed due to the present concern of morphology, syntax and semantics. A translation system has been implemented on the multi-agent system development framework named MaSMT. Experiments show that the multi-agent solution for MT gives promising results for translating sentences of an average length and further research has been carried out to accommodate translation of long sentences.