# Energy-Based Reranking: Improving Neural Machine Translation Using Energy-Based Models

arXiv: https://arxiv.org/abs/2009.13267 · HTML: https://mlsanity.com/paper/2009.13267/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Sep 2020.

## Built on by (most cited first, 30 of 44)

- [Language Models as Agent Models](https://mlsanity.com/paper/2212.01681/) (2022)
- [A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Models](https://mlsanity.com/paper/2201.05337/) (2022)
- [Calibrating Sequence likelihood Improves Conditional Language Generation](https://mlsanity.com/paper/2210.00045/) (2022)
- [Survey of Low-Resource Machine Translation](https://mlsanity.com/paper/2109.00486/) (2021)
- [On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting](https://mlsanity.com/paper/2206.00761/) (2022)
- [RankGen: Improving Text Generation with Large Ranking Models](https://mlsanity.com/paper/2205.09726/) (2022)
- [Sampling-Based Approximations to Minimum Bayes Risk Decoding for Neural Machine Translation](https://mlsanity.com/paper/2108.04718/) (2021)
- [SummaReranker: A Multi-Task Mixture-of-Experts Re-ranking Framework for Abstractive Summarization](https://mlsanity.com/paper/2203.06569/) (2022)
- [Machine Translation Decoding beyond Beam Search](https://mlsanity.com/paper/2104.05336/) (2021)
- [LENS: A Learnable Evaluation Metric for Text Simplification](https://mlsanity.com/paper/2212.09739/) (2022)
- [Quality-Aware Decoding for Neural Machine Translation](https://mlsanity.com/paper/2205.00978/) (2022)
- [Energy-Based Transformers are Scalable Learners and Thinkers](https://mlsanity.com/paper/2507.02092/) (2025)
- [CoNT: Contrastive Neural Text Generation](https://mlsanity.com/paper/2205.14690/) (2022)
- [Aligning Neural Machine Translation Models: Human Feedback in Training and Inference](https://mlsanity.com/paper/2311.09132/) (2023)
- [Interpretable Math Word Problem Solution Generation Via Step-by-step Planning](https://mlsanity.com/paper/2306.00784/) (2023)
- [MacLaSa: Multi-Aspect Controllable Text Generation via Efficient Sampling from Compact Latent Space](https://mlsanity.com/paper/2305.12785/) (2023)
- [Efficient Nearest Neighbor Search for Cross-Encoder Models using Matrix Factorization](https://mlsanity.com/paper/2210.12579/) (2022)
- [R-U-SURE? Uncertainty-Aware Code Suggestions By Maximizing Utility Across Random User Intents](https://mlsanity.com/paper/2303.00732/) (2023)
- [Uncertainty Determines the Adequacy of the Mode and the Tractability of Decoding in Sequence-to-Sequence Models](https://mlsanity.com/paper/2204.00471/) (2022)
- [Quality-Aware Translation Models: Efficient Generation and Quality Estimation in a Single Model](https://mlsanity.com/paper/2310.06707/) (2023)
- [Transcormer: Transformer for Sentence Scoring with Sliding Language Modeling](https://mlsanity.com/paper/2205.12986/) (2022)
- [Language Model Decoding as Direct Metrics Optimization](https://mlsanity.com/paper/2310.01041/) (2023)
- [Preference Optimization for Molecule Synthesis with Conditional Residual Energy-based Models](https://mlsanity.com/paper/2406.02066/) (2024)
- [EEL: Efficiently Encoding Lattices for Reranking](https://mlsanity.com/paper/2306.00947/) (2023)
- [DOCE: Finding the Sweet Spot for Execution-Based Code Generation](https://mlsanity.com/paper/2408.13745/) (2024)
- [Reranking Laws for Language Generation: A Communication-Theoretic Perspective](https://mlsanity.com/paper/2409.07131/) (2024)
- [Improving abstractive summarization with energy-based re-ranking](https://mlsanity.com/paper/2210.15553/) (2022)
- [Multi-Amateur Contrastive Decoding for Text Generation](https://mlsanity.com/paper/2507.21086/) (2025)
- [Sampling from Discrete Energy-Based Models with Quality/Efficiency Trade-offs](https://mlsanity.com/paper/2112.05702/) (2021)
- [RMBR: A Regularized Minimum Bayes Risk Reranking Framework for Machine Translation](https://mlsanity.com/paper/2203.00201/) (2022)

## Abstract (arXiv)

The discrepancy between maximum likelihood estimation (MLE) and task measures such as BLEU score has been studied before for autoregressive neural machine translation (NMT) and resulted in alternative training algorithms (Ranzato et al., 2016; Norouzi et al., 2016; Shen et al., 2016; Wu et al., 2018). However, MLE training remains the de facto approach for autoregressive NMT because of its computational efficiency and stability. Despite this mismatch between the training objective and task measure, we notice that the samples drawn from an MLE-based trained NMT support the desired distribution -- there are samples with much higher BLEU score comparing to the beam decoding output. To benefit from this observation, we train an energy-based model to mimic the behavior of the task measure (i.e., the energy-based model assigns lower energy to samples with higher BLEU score), which is resulted in a re-ranking algorithm based on the samples drawn from NMT: energy-based re-ranking (EBR). We use both marginal energy models (over target sentence) and joint energy models (over both source and target sentences). Our EBR with the joint energy model consistently improves the performance of the Transformer-based NMT: +4 BLEU points on IWSLT'14 German-English, +3.0 BELU points on Sinhala-English, +1.2 BLEU on WMT'16 English-German tasks.