# Beyond Error Propagation in Neural Machine Translation: Characteristics of Language Also Matter

arXiv: https://arxiv.org/abs/1809.00120 · HTML: https://mlsanity.com/paper/1809.00120/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Sep 2018.

## Built on by (most cited first, 18 of 18)

- [A Survey on Neural Speech Synthesis](https://mlsanity.com/paper/2106.15561/) (2021)
- [Survey of Low-Resource Machine Translation](https://mlsanity.com/paper/2109.00486/) (2021)
- [DeepRapper: Neural Rap Generation with Rhyme and Rhythm Modeling](https://mlsanity.com/paper/2107.01875/) (2021)
- [Arrows of Time for Large Language Models](https://mlsanity.com/paper/2401.17505/) (2024)
- [LayoutNUWA: Revealing the Hidden Layout Expertise of Large Language Models](https://mlsanity.com/paper/2309.09506/) (2023)
- [Discovering Non-monotonic Autoregressive Orderings with Variational Inference](https://mlsanity.com/paper/2110.15797/) (2021)
- [STable: Table Generation Framework for Encoder-Decoder Models](https://mlsanity.com/paper/2206.04045/) (2022)
- [Parallel and High-Fidelity Text-to-Lip Generation](https://mlsanity.com/paper/2107.06831/) (2021)
- [ToXCL: A Unified Framework for Toxic Speech Detection and Explanation](https://mlsanity.com/paper/2403.16685/) (2024)
- [Segment-Level Diffusion: A Framework for Controllable Long-Form Generation with Diffusion Language Models](https://mlsanity.com/paper/2412.11333/) (2024)
- [JRE-L: Journalist, Reader, and Editor LLMs in the Loop for Science Journalism for the General Audience](https://mlsanity.com/paper/2501.16865/) (2025)
- [LLM-Collaboration on Automatic Science Journalism for the General Audience](https://mlsanity.com/paper/2407.09756/) (2024)
- [Reverse Modeling in Large Language Models](https://mlsanity.com/paper/2410.09817/) (2024)
- [Improving Scheduled Sampling with Elastic Weight Consolidation for Neural Machine Translation](https://mlsanity.com/paper/2109.06308/) (2021)
- [UBARv2: Towards Mitigating Exposure Bias in Task-Oriented Dialogs](https://mlsanity.com/paper/2209.07239/) (2022)
- [On the Temporality for Sketch Representation Learning](https://mlsanity.com/paper/2512.04007/) (2025)
- [Scheduling Thoughts: Learning the Order of Thought in Diffusion Language Models](https://mlsanity.com/paper/2606.23567/) (2026)
- [Doc2FRC: Length-Consistent Document-Level Machine Translation via Fixed-Range Chunking](https://mlsanity.com/paper/2609.12674/) (2026)

## Abstract (arXiv)

Neural machine translation usually adopts autoregressive models and suffers from exposure bias as well as the consequent error propagation problem. Many previous works have discussed the relationship between error propagation and the accuracy drop (i.e., the left part of the translated sentence is often better than its right part in left-to-right decoding models) problem. In this paper, we conduct a series of analyses to deeply understand this problem and get several interesting findings. (1) The role of error propagation on accuracy drop is overstated in the literature, although it indeed contributes to the accuracy drop problem. (2) Characteristics of a language play a more important role in causing the accuracy drop: the left part of the translation result in a right-branching language (e.g., English) is more likely to be more accurate than its right part, while the right part is more accurate for a left-branching language (e.g., Japanese). Our discoveries are confirmed on different model structures including Transformer and RNN, and in other sequence generation tasks such as text summarization.