# Multilingual Neural Machine Translation With Soft Decoupled Encoding

arXiv: https://arxiv.org/abs/1902.03499 · HTML: https://mlsanity.com/paper/1902.03499/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Feb 2019.

## Built on by (most cited first, 21 of 21)

- [Neural Machine Translation for Low-Resource Languages: A Survey](https://mlsanity.com/paper/2106.15115/) (2021)
- [Multi-view Subword Regularization](https://mlsanity.com/paper/2103.08490/) (2021)
- [Language Tags Matter for Zero-Shot Neural Machine Translation](https://mlsanity.com/paper/2106.07930/) (2021)
- [Overlap-based Vocabulary Generation Improves Cross-lingual Transfer Among Related Languages](https://mlsanity.com/paper/2203.01976/) (2022)
- [Exploiting Language Relatedness for Low Web-Resource Language Model Adaptation: An Indic Languages Study](https://mlsanity.com/paper/2106.03958/) (2021)
- [Meta Back-translation](https://mlsanity.com/paper/2102.07847/) (2021)
- [Multilingual Machine Translation with Hyper-Adapters](https://mlsanity.com/paper/2205.10835/) (2022)
- [Alternative Input Signals Ease Transfer in Multilingual Machine Translation](https://mlsanity.com/paper/2110.07804/) (2021)
- [Language-Family Adapters for Low-Resource Multilingual Neural Machine Translation](https://mlsanity.com/paper/2209.15236/) (2022)
- [Multilingual Translation via Grafting Pre-trained Language Models](https://mlsanity.com/paper/2109.05256/) (2021)
- [CipherDAug: Ciphertext based Data Augmentation for Neural Machine Translation](https://mlsanity.com/paper/2204.00665/) (2022)
- [On the Pareto Front of Multilingual Neural Machine Translation](https://mlsanity.com/paper/2304.03216/) (2023)
- [Neural Machine Translation for the Indigenous Languages of the Americas: An Introduction](https://mlsanity.com/paper/2306.06804/) (2023)
- [Lens: Rethinking Multilingual Enhancement for Large Language Models](https://mlsanity.com/paper/2410.04407/) (2024)
- [Exploiting Multilingualism in Low-resource Neural Machine Translation via Adversarial Learning](https://mlsanity.com/paper/2303.18011/) (2023)
- [CharSpan: Utilizing Lexical Similarity to Enable Zero-Shot Machine Translation for Extremely Low-resource Languages](https://mlsanity.com/paper/2305.05214/) (2023)
- [Can the Variation of Model Weights be used as a Criterion for Self-Paced Multilingual NMT?](https://mlsanity.com/paper/2410.04147/) (2024)
- [A Neural Network-Based Linguistic Similarity Measure for Entrainment in Conversations](https://mlsanity.com/paper/2109.01924/) (2021)
- [Variable-length Neural Interlingua Representations for Zero-shot Neural Machine Translation](https://mlsanity.com/paper/2305.10190/) (2023)
- [Deterministic Reversible Data Augmentation for Neural Machine Translation](https://mlsanity.com/paper/2406.02517/) (2024)
- [Optimizing the Training Schedule of Multilingual NMT using Reinforcement Learning](https://mlsanity.com/paper/2410.06118/) (2024)

## Abstract (arXiv)

Multilingual training of neural machine translation (NMT) systems has led to impressive accuracy improvements on low-resource languages. However, there are still significant challenges in efficiently learning word representations in the face of paucity of data. In this paper, we propose Soft Decoupled Encoding (SDE), a multilingual lexicon encoding framework specifically designed to share lexical-level information intelligently without requiring heuristic preprocessing such as pre-segmenting the data. SDE represents a word by its spelling through a character encoding, and its semantic meaning through a latent embedding space shared by all languages. Experiments on a standard dataset of four low-resource languages show consistent improvements over strong multilingual NMT baselines, with gains of up to 2 BLEU on one of the tested languages, achieving the new state-of-the-art on all four language pairs.