# Neural Machine Translation with Adequacy-Oriented Learning

arXiv: https://arxiv.org/abs/1811.08541 · HTML: https://mlsanity.com/paper/1811.08541/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Nov 2018.

## Built on by (most cited first, 8 of 8)

- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation](https://mlsanity.com/paper/2106.05093/) (2021)
- [Prevent the Language Model from being Overconfident in Neural Machine Translation](https://mlsanity.com/paper/2105.11098/) (2021)
- [Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methods](https://mlsanity.com/paper/2203.05227/) (2022)
- [Aligning Neural Machine Translation Models: Human Feedback in Training and Inference](https://mlsanity.com/paper/2311.09132/) (2023)
- [As Little as Possible, as Much as Necessary: Detecting Over- and Undertranslations with Contrastive Conditioning](https://mlsanity.com/paper/2203.01927/) (2022)
- [Multi-Granularity Optimization for Non-Autoregressive Translation](https://mlsanity.com/paper/2210.11017/) (2022)
- [Scaling Unsupervised Word Alignment to Documents via Structural Constraints](https://mlsanity.com/paper/2608.21023/) (2026)

## Abstract (arXiv)

Although Neural Machine Translation (NMT) models have advanced state-of-the-art performance in machine translation, they face problems like the inadequate translation. We attribute this to that the standard Maximum Likelihood Estimation (MLE) cannot judge the real translation quality due to its several limitations. In this work, we propose an adequacy-oriented learning mechanism for NMT by casting translation as a stochastic policy in Reinforcement Learning (RL), where the reward is estimated by explicitly measuring translation adequacy. Benefiting from the sequence-level training of RL strategy and a more accurate reward designed specifically for translation, our model outperforms multiple strong baselines, including (1) standard and coverage-augmented attention models with MLE-based training, and (2) advanced reinforcement and adversarial training strategies with rewards based on both word-level BLEU and character-level chrF3. Quantitative and qualitative analyses on different language pairs and NMT architectures demonstrate the effectiveness and universality of the proposed approach.