@InProceedings{gu-cho-li:2017:EMNLP2017,
  author    = {Gu, Jiatao  and  Cho, Kyunghyun  and  Li, Victor O.K.},
  title     = {Trainable Greedy Decoding for Neural Machine Translation},
  booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing},
  month     = {September},
  year      = {2017},
  address   = {Copenhagen, Denmark},
  publisher = {Association for Computational Linguistics},
  pages     = {1968--1978},
  abstract  = {Recent research in neural machine translation has largely focused on two
	aspects; neural network architectures and end-to-end learning algorithms. The
	problem of decoding, however, has received relatively little attention from the
	research community. In this paper, we solely focus on the problem of decoding
	given a trained neural machine translation model. Instead of trying to build a
	new decoding algorithm for any specific decoding objective, we propose the idea
	of trainable decoding algorithm in which we train a decoding algorithm to find
	a translation that maximizes an arbitrary decoding objective. More
	specifically, we design an actor that observes and manipulates the hidden state
	of the neural machine translation decoder and propose to train it using a
	variant of deterministic policy gradient. We extensively evaluate the proposed
	algorithm using four language pairs and two decoding objectives and show that
	we can indeed train a trainable greedy decoder that generates a better
	translation (in terms of a target decoding objective) with minimal
	computational overhead.},
  url       = {https://www.aclweb.org/anthology/D17-1210}
}