A Stable and Effective Learning Strategy for Trainable Greedy Decoding

By Yun Chen, Victor O. K. Li, Kyunghyun Cho, Samuel R. Bowman. 2018

31 citations recorded by the source corpus.

Beam search is a widely used approximate search strategy for neural network decoders, and it generally outperforms simple greedy decoding on tasks like machine translation. However, this improvement comes at substantial computational cost. In this paper, we propose a flexible new method that allows us to reap nearly the full benefits of beam search with nearly no additional computational cost. The method revolves around a small neural network actor that is trained to observe and manipulate the hidden state of a previously-trained decoder. To train this actor network, we introduce the use of a pseudo-parallel corpus built using the output of beam search on a base model, ranked by a target quality metric like BLEU. Our method is inspired by earlier work on this problem, but requires no reinforcement learning, and can be trained reliably on a range of models. Experiments on three parallel corpora and three architectures show that the method yields substantial improvements in translation quality and speed over each base system.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, 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 Artificial Intelligence

In Computer Vision and Pattern Recognition

In Natural Language Processing

Citations in the corpus

fairseq: A Fast, Extensible Toolkit for Sequence Modeling (2019, methodology): “FAIRSEQ has been used in many applications, such as machine translation (Gehring et al., 2017; Edunov et al., 2018b,a; Chen et al., 2018; Ott et al., 2018a; Song et al., 2018; Wu et al., 2019), language modeling (Dauphin et al.”
Plug and Play Language Models: A Simple Approach to Controlled Text Generation (2019, background): “In earlier works Gu et al. (2016; 2017); Chen et al. (2018) explored the idea of using a small neural network to steer an LM. Yu et al. (2016), and more recently Yu et al. (2019); Yee et al. (2019); Ng et al. (2019), leveraged the Shannon Noisy Channel Theory (Shannon, 1948) for improving…”
Importance of Search and Evaluation Strategies in Neural Dialogue Modeling (2018, methodology): “Greedy search has been found significantly suboptimal within the field of machine translation (see, e.g., Table 1 in Chen et al., 2018), where similar neural sequence models are frequently used.”
ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic (2021, background): “Several studies have explored the idea of steering an LM using small neural networks [10, 25].”
Importance of a Search Strategy in Neural Dialogue Modelling (2018, methodology): “Greedy search has been found significantly suboptimal within the field of machine translation (see, e.g., Table 1 in Chen et al., 2018), where similar neural sequence models are frequently used.”
Can Unconditional Language Models Recover Arbitrary Sentences? (2019, methodology): “Unlike forward estimation, backward estimation is a combinatorial optimization problem and cannot be solved easily with a recurrent language model (Cho, 2016; Chen et al., 2018).”
Neural Machine Translation: A Review (2019, background): “which modifies the hidden states in an already trained model [189, 191].”