# Understanding and Addressing the Under-Translation Problem from the Perspective of Decoding Objective

arXiv: https://arxiv.org/abs/2405.18922 · HTML: https://mlsanity.com/paper/2405.18922/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 24 references that are in the map.
- First posted on arXiv 29 May 2024.

## Builds on (most cited first, 12 of 12)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [Modeling Coverage for Neural Machine Translation](https://mlsanity.com/paper/1601.04811/) (2016)
- [Adapting Large Language Models for Document-Level Machine Translation](https://mlsanity.com/paper/2401.06468/) (2024)
- [Neural Machine Translation with Reconstruction](https://mlsanity.com/paper/1611.01874/) (2016)
- [Structure-Invariant Testing for Machine Translation](https://mlsanity.com/paper/1907.08710/) (2019)
- [Modeling Past and Future for Neural Machine Translation](https://mlsanity.com/paper/1711.09502/) (2017)

## Built on by (most cited first, 1 of 1)

- [STAR : Sentence Translation Alignment Rate for Document-to-Document Machine Translation](https://mlsanity.com/paper/2608.27161/) (2026)

## Abstract (arXiv)

Neural Machine Translation (NMT) has made remarkable progress over the past years. However, under-translation and over-translation remain two challenging problems in state-of-the-art NMT systems. In this work, we conduct an in-depth analysis on the underlying cause of under-translation in NMT, providing an explanation from the perspective of decoding objective. To optimize the beam search objective, the model tends to overlook words it is less confident about, leading to the under-translation phenomenon. Correspondingly, the model's confidence in predicting the End Of Sentence (EOS) diminishes when under-translation occurs, serving as a mild penalty for under-translated candidates. Building upon this analysis, we propose employing the confidence of predicting EOS as a detector for under-translation, and strengthening the confidence-based penalty to penalize candidates with a high risk of under-translation. Experiments on both synthetic and real-world data show that our method can accurately detect and rectify under-translated outputs, with minor impact on other correct translations.