# Towards Decoding as Continuous Optimization in Neural Machine Translation

arXiv: https://arxiv.org/abs/1701.02854 · HTML: https://mlsanity.com/paper/1701.02854/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jan 2017.

## Built on by (most cited first, 15 of 15)

- [SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control](https://mlsanity.com/paper/2210.17432/) (2022)
- [COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics](https://mlsanity.com/paper/2202.11705/) (2022)
- [Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey](https://mlsanity.com/paper/2210.07700/) (2022)
- [Controlled Text Generation as Continuous Optimization with Multiple Constraints](https://mlsanity.com/paper/2108.01850/) (2021)
- [Gradient-Based Constrained Sampling from Language Models](https://mlsanity.com/paper/2205.12558/) (2022)
- [Constrained Decoding for Secure Code Generation](https://mlsanity.com/paper/2405.00218/) (2024)
- [FIFA: Fast Inference Approximation for Action Segmentation](https://mlsanity.com/paper/2108.03894/) (2021)
- [Top-Down Semantic Refinement for Image Captioning](https://mlsanity.com/paper/2510.22391/) (2025)
- [Guiding Teacher Forcing with Seer Forcing for Neural Machine Translation](https://mlsanity.com/paper/2106.06751/) (2021)
- [Confidence Based Bidirectional Global Context Aware Training Framework for Neural Machine Translation](https://mlsanity.com/paper/2202.13663/) (2022)
- [nabla-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Latent Space](https://mlsanity.com/paper/2603.04948/) (2026)
- [PlaSma: Making Small Language Models Better Procedural Knowledge Models for (Counterfactual) Planning](https://mlsanity.com/paper/2305.19472/) (2023)
- [Structured Voronoi Sampling](https://mlsanity.com/paper/2306.03061/) (2023)
- [Learning Energy-Based Approximate Inference Networks for Structured Applications in NLP](https://mlsanity.com/paper/2108.12522/) (2021)
- [Spiral Language Modeling](https://mlsanity.com/paper/2112.10543/) (2021)

## Abstract (arXiv)

We propose a novel decoding approach for neural machine translation (NMT) based on continuous optimisation. We convert decoding - basically a discrete optimization problem - into a continuous optimization problem. The resulting constrained continuous optimisation problem is then tackled using gradient-based methods. Our powerful decoding framework enables decoding intractable models such as the intersection of left-to-right and right-to-left (bidirectional) as well as source-to-target and target-to-source (bilingual) NMT models. Our empirical results show that our decoding framework is effective, and leads to substantial improvements in translations generated from the intersected models where the typical greedy or beam search is not feasible. We also compare our framework against reranking, and analyse its advantages and disadvantages.