Decoding with Value Networks for Neural Machine Translation

By Di He, Hanqing Lu, Yingce Xia, Tao Qin, Liwei Wang, Tie-Yan Liu. 2017

53 citations recorded by the source corpus.

Subfields: Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

1. Tao Qin
2. Tie-Yan Liu
3. Xu Tan
4. Lijun Wu
5. Yingce Xia
6. Fei Tian
7. Di He
8. J. Lai

Citations in the corpus

• Microsoft Research Asia’s Systems for WMT19 (2019, methodology): “Furthermore, some other techniques such as de-liberation learning (Xia et al., 2017b), adversarial learning (Wu et al., 2018b), and reinforcement learning (He et al., 2017; Wu et al., 2018a) could also hep and are worthy of exploration.”
• Dual Transfer Learning for Neural Machine Translation with Marginal Distribution Regularization (2018, methodology): “Beyond the standard encoder-decoder architecture, more elaborate decoder architectures have been proposed to promote the performance of NMT systems (Xia et al. 2017c; He et al. 2017).”
• Small Sample Learning in Big Data Era (2018, methodology): “Besides, He et al. (2017b) presented a fast yet accurate text detector with attention mechanism encoding strong supervised information of text in training that predicted wordlevel bounding boxes in one shot.”
• Neural Machine Translation with Adequacy-Oriented Learning (2018, unknown): “For example, Tu et al. (2016) 2017) use a prediction network to estimate the future cost of translating the uncovered source words.”
• A Study of Reinforcement Learning for Neural Machine Translation (2018, background): “Recently, neural machine translation (NMT) (Bah-danau et al., 2015; Hassan et al., 2018; Wu et al., 2016; He et al., 2017; Xia et al., 2016, 2017; Wu et al., 2018b,a) has become more and more popular given its superior performance without the demand of heavily hand-crafted engineering efforts.”
• Survey on reinforcement learning for language processing (2021, background): “NMT systems became a major area of development since the emergence of deep neural networks in 2012 [3, 128, 44, 43, 61].”
• Sentence-wise Smooth Regularization for Sequence to Sequence Learning (2018, methodology): “All rights reserved. tasks, such as exposure bias (Wiseman and Rush 2016; Wu et al. 2018; Guo et al. 2019), loss-evaluation mismatch (Wiseman and Rush 2016; Vijayakumar et al. 2016), and myopic bias (He et al. 2017). In this paper, we investigate the MLE loss for sequence to sequence tasks from an o”
• Deliberation Networks: Sequence Generation Beyond One-Pass Decoding (2017, background): “Although there exist many works to improve the attention based encoder-decoder framework for sequence generation, such as changing the training loss [28, 18, 22] or the decoding objective [14, 7], not much attention has been paid to the structure of the encoder-decoder framework.”
• Neural Machine Translation: A Review (2019, unknown): “[176] used reinforcement learning to estimate the long-term value of a candidate.”