# Trainable Greedy Decoding for Neural Machine Translation

arXiv: https://arxiv.org/abs/1702.02429 · HTML: https://mlsanity.com/paper/1702.02429/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Feb 2017.

## Built on by (most cited first, 23 of 23)

- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [Extracting Latent Steering Vectors from Pretrained Language Models](https://mlsanity.com/paper/2205.05124/) (2022)
- [Offline RL for Natural Language Generation with Implicit Language Q Learning](https://mlsanity.com/paper/2206.11871/) (2022)
- [LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models](https://mlsanity.com/paper/2311.18232/) (2023)
- [Unleashing the potential of prompt engineering for large language models](https://mlsanity.com/paper/2310.14735/) (2023)
- [Merge, Ensemble, and Cooperate! A Survey on Collaborative Strategies in the Era of Large Language Models](https://mlsanity.com/paper/2407.06089/) (2024)
- [Zero-Shot Goal-Directed Dialogue via RL on Imagined Conversations](https://mlsanity.com/paper/2311.05584/) (2023)
- [Zero-Shot Video Captioning with Evolving Pseudo-Tokens](https://mlsanity.com/paper/2207.11100/) (2022)
- [An Overview on Language Models: Recent Developments and Outlook](https://mlsanity.com/paper/2303.05759/) (2023)
- [A Mixture-of-Expert Approach to RL-based Dialogue Management](https://mlsanity.com/paper/2206.00059/) (2022)
- [Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL](https://mlsanity.com/paper/2505.18098/) (2025)
- [Transformation vs Tradition: Artificial General Intelligence (AGI) for Arts and Humanities](https://mlsanity.com/paper/2310.19626/) (2023)
- [Advancements in Scientific Controllable Text Generation Methods](https://mlsanity.com/paper/2307.05538/) (2023)
- [Incremental Beam Manipulation for Natural Language Generation](https://mlsanity.com/paper/2102.02574/) (2021)
- [Long-term Control for Dialogue Generation: Methods and Evaluation](https://mlsanity.com/paper/2205.07352/) (2022)
- [Amortized Noisy Channel Neural Machine Translation](https://mlsanity.com/paper/2112.08670/) (2021)
- [Rephrasing the Reference for Non-Autoregressive Machine Translation](https://mlsanity.com/paper/2211.16863/) (2022)
- [Plug and Play Counterfactual Text Generation for Model Robustness](https://mlsanity.com/paper/2206.10429/) (2022)
- [HU at SemEval-2024 Task 8A: Can Contrastive Learning Learn Embeddings to Detect Machine-Generated Text?](https://mlsanity.com/paper/2402.11815/) (2024)
- [Steered Generation via Gradient Descent on Sparse Features](https://mlsanity.com/paper/2502.18644/) (2025)
- [Learning Energy-Based Approximate Inference Networks for Structured Applications in NLP](https://mlsanity.com/paper/2108.12522/) (2021)
- [Describe me an Aucklet: Generating Grounded Perceptual Category Descriptions](https://mlsanity.com/paper/2303.04053/) (2023)
- [Steered Generation via Gradient-Based Optimization on Sparse Query Features](https://mlsanity.com/paper/2605.23040/) (2026)

## Abstract (arXiv)

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.