Neural machine translation (NMT) models have recently been shown to be very successful in machine translation (MT). The use of LSTMs in machine translation has significantly improved the translation performance for longer sentences by being able to capture the context and long range correlations of the sentences in their hidden layers. The attention model based NMT system has become state-of-the-art, performing equal or better than other statistical MT approaches. In this paper, we studied the performance of the attention-model based NMT system on the Indian language pair, Hindi and Bengali. We analysed the types of errors that occur in morphologically rich languages when there is a scarcity of large parallel training corpus. We then carried out certain post-processing heuristic steps to improve the quality of the translated statements and suggest further measures.
展开▼