# Explicit Sentence Compression for Neural Machine Translation

arXiv: https://arxiv.org/abs/1912.11980 · HTML: https://mlsanity.com/paper/1912.11980/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Dec 2019.

## Built on by (most cited first, 11 of 11)

- [Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey](https://mlsanity.com/paper/2104.06951/) (2021)
- [Machine Translation Testing via Syntactic Tree Pruning](https://mlsanity.com/paper/2401.00751/) (2024)
- [An Enhanced Text Compression Approach Using Transformer-based Language Models](https://mlsanity.com/paper/2412.15250/) (2024)
- [Prompting LLMs: Length Control for Isometric Machine Translation](https://mlsanity.com/paper/2506.04855/) (2025)
- [Dual-branch Prompting for Multimodal Machine Translation](https://mlsanity.com/paper/2507.17588/) (2025)
- [Exploring the Necessity of Visual Modality in Multimodal Machine Translation using Authentic Datasets](https://mlsanity.com/paper/2404.06107/) (2024)
- [Segment First or Comprehend First? Explore the Limit of Unsupervised Word Segmentation with Large Language Models](https://mlsanity.com/paper/2505.19631/) (2025)
- [Channel-aware Decoupling Network for Multi-turn Dialogue Comprehension](https://mlsanity.com/paper/2301.03953/) (2023)
- [Evaluating the Efficacy of Length-Controllable Machine Translation](https://mlsanity.com/paper/2305.02300/) (2023)
- [From Lengthy to Lucid: A Systematic Literature Review on NLP Techniques for Taming Long Sentences](https://mlsanity.com/paper/2312.05172/) (2023)
- [TextEconomizer: Enhancing Lossy Text Compression with Denoising Transformers and Entropy Coding](https://mlsanity.com/paper/2606.08184/) (2026)

## Abstract (arXiv)

State-of-the-art Transformer-based neural machine translation (NMT) systems still follow a standard encoder-decoder framework, in which source sentence representation can be well done by an encoder with self-attention mechanism. Though Transformer-based encoder may effectively capture general information in its resulting source sentence representation, the backbone information, which stands for the gist of a sentence, is not specifically focused on. In this paper, we propose an explicit sentence compression method to enhance the source sentence representation for NMT. In practice, an explicit sentence compression goal used to learn the backbone information in a sentence. We propose three ways, including backbone source-side fusion, target-side fusion, and both-side fusion, to integrate the compressed sentence into NMT. Our empirical tests on the WMT English-to-French and English-to-German translation tasks show that the proposed sentence compression method significantly improves the translation performances over strong baselines.