Y-C. Tam and Y. Lei, “Neural network joint modeling via context-dependent projection,” In Proc. 40th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2015.
Neural network joint modeling (NNJM) has produced huge improvement in machine translation performance. As in standard neural network language modeling, a context-independent linear projection is applied to project a sparse input vector into a continuous representation at each word position. Because neighboring words are dependent on each other, context-independent projection may not be optimal. We propose a context-dependent linear projection approach which considers neighboring words. Experimental results showed that the proposed approach further improves NNJM by 0.5 BLEU for English-Iraqi Arabic translation in N-best rescoring. Compared to a baseline using hierarchical phrases and sparse features, NNJM with our proposed approach has achieved a 2 BLEU improvement.