Online and Linear-Time Attention by Enforcing Monotonic Alignments. Raffel, C., Luong, M., Liu, P. J., Weiss, R. J., & Eck, D. arXiv:1704.00784 [cs], June, 2017. arXiv: 1704.00784
Online and Linear-Time Attention by Enforcing Monotonic Alignments [link]Paper  abstract   bibtex   
Recurrent neural network models with an attention mechanism have proven to be extremely effective on a wide variety of sequence-tosequence problems. However, the fact that soft attention mechanisms perform a pass over the entire input sequence when producing each element in the output sequence precludes their use in online settings and results in a quadratic time complexity. Based on the insight that the alignment between input and output sequence elements is monotonic in many problems of interest, we propose an end-to-end differentiable method for learning monotonic alignments which, at test time, enables computing attention online and in linear time. We validate our approach on sentence summarization, machine translation, and online speech recognition problems and achieve results competitive with existing sequence-tosequence models.
@article{raffel_online_2017,
	title = {Online and {Linear}-{Time} {Attention} by {Enforcing} {Monotonic} {Alignments}},
	url = {http://arxiv.org/abs/1704.00784},
	abstract = {Recurrent neural network models with an attention mechanism have proven to be extremely effective on a wide variety of sequence-tosequence problems. However, the fact that soft attention mechanisms perform a pass over the entire input sequence when producing each element in the output sequence precludes their use in online settings and results in a quadratic time complexity. Based on the insight that the alignment between input and output sequence elements is monotonic in many problems of interest, we propose an end-to-end differentiable method for learning monotonic alignments which, at test time, enables computing attention online and in linear time. We validate our approach on sentence summarization, machine translation, and online speech recognition problems and achieve results competitive with existing sequence-tosequence models.},
	language = {en},
	urldate = {2022-01-19},
	journal = {arXiv:1704.00784 [cs]},
	author = {Raffel, Colin and Luong, Minh-Thang and Liu, Peter J. and Weiss, Ron J. and Eck, Douglas},
	month = jun,
	year = {2017},
	note = {arXiv: 1704.00784},
	keywords = {/unread, Computer Science - Computation and Language, Computer Science - Machine Learning, ⛔ No DOI found},
}

Downloads: 0