@InProceedings{tjandra-sakti-nakamura:2017:I17-1,
  author    = {Tjandra, Andros  and  Sakti, Sakriani  and  Nakamura, Satoshi},
  title     = {Local Monotonic Attention Mechanism for End-to-End Speech And Language Processing},
  booktitle = {Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)},
  month     = {November},
  year      = {2017},
  address   = {Taipei, Taiwan},
  publisher = {Asian Federation of Natural Language Processing},
  pages     = {431--440},
  abstract  = {Recently, encoder-decoder neural networks have shown impressive performance on
	many sequence-related tasks. The architecture commonly uses an attentional
	mechanism which allows the model to learn alignments between the source and the
	target sequence. Most attentional mechanisms used today is based on a global
	attention property which requires a computation of a weighted summarization of
	the whole input sequence generated by encoder states. However, it is
	computationally expensive and often produces misalignment on the longer input
	sequence. Furthermore, it does not fit with monotonous or left-to-right nature
	in several tasks, such as automatic speech recognition (ASR),
	grapheme-to-phoneme (G2P), etc. In this paper, we propose a novel attention
	mechanism that has local and monotonic properties. Various  ways  to  control 
	those  properties  are                                                        also   
	           
	explored.
	Experimental results
	on
	ASR, G2P
	and
	machine translation between two languages with similar sentence structures,
	demonstrate that the proposed encoder-decoder model with local monotonic
	attention could achieve significant performance improvements and reduce the
	computational complexity in comparison with the one that used the standard
	global attention architecture.},
  url       = {http://www.aclweb.org/anthology/I17-1044}
}