# Emergent Communication Pretraining for Few-Shot Machine Translation

arXiv: https://arxiv.org/abs/2011.00890 · HTML: https://mlsanity.com/paper/2011.00890/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Nov 2020.

## Built on by (most cited first, 13 of 13)

- [Visually Grounded Reasoning across Languages and Cultures](https://mlsanity.com/paper/2109.13238/) (2021)
- [Pretrained Transformers as Universal Computation Engines](https://mlsanity.com/paper/2103.05247/) (2021)
- [Cross-Modal Fine-Tuning: Align then Refine](https://mlsanity.com/paper/2302.05738/) (2023)
- [Linking Emergent and Natural Languages via Corpus Transfer](https://mlsanity.com/paper/2203.13344/) (2022)
- [A Review of the Applications of Deep Learning-Based Emergent Communication](https://mlsanity.com/paper/2407.03302/) (2024)
- [Towards More Human-like AI Communication: A Review of Emergent Communication Research](https://mlsanity.com/paper/2308.02541/) (2023)
- [Emergent Language: A Survey and Taxonomy](https://mlsanity.com/paper/2409.02645/) (2024)
- [Low-resource Neural Machine Translation with Cross-modal Alignment](https://mlsanity.com/paper/2210.06716/) (2022)
- [Learning to translate by learning to communicate](https://mlsanity.com/paper/2207.07025/) (2022)
- [Recommendations for Systematic Research on Emergent Language](https://mlsanity.com/paper/2206.11302/) (2022)
- [On Bilingual Lexicon Induction with Large Language Models](https://mlsanity.com/paper/2310.13995/) (2023)
- [ELCC: the Emergent Language Corpus Collection](https://mlsanity.com/paper/2407.04158/) (2024)
- [XferBench: a Data-Driven Benchmark for Emergent Language](https://mlsanity.com/paper/2407.03456/) (2024)

## Abstract (arXiv)

While state-of-the-art models that rely upon massively multilingual pretrained encoders achieve sample efficiency in downstream applications, they still require abundant amounts of unlabelled text. Nevertheless, most of the world's languages lack such resources. Hence, we investigate a more radical form of unsupervised knowledge transfer in the absence of linguistic data. In particular, for the first time we pretrain neural networks via emergent communication from referential games. Our key assumption is that grounding communication on images---as a crude approximation of real-world environments---inductively biases the model towards learning natural languages. On the one hand, we show that this substantially benefits machine translation in few-shot settings. On the other hand, this also provides an extrinsic evaluation protocol to probe the properties of emergent languages ex vitro. Intuitively, the closer they are to natural languages, the higher the gains from pretraining on them should be. For instance, in this work we measure the influence of communication success and maximum sequence length on downstream performances. Finally, we introduce a customised adapter layer and annealing strategies for the regulariser of maximum-a-posteriori inference during fine-tuning. These turn out to be crucial to facilitate knowledge transfer and prevent catastrophic forgetting. Compared to a recurrent baseline, our method yields gains of 59.0%~147.6% in BLEU score with only 500 NMT training instances and 65.1%~196.7% with 1,000 NMT training instances across four language pairs. These proof-of-concept results reveal the potential of emergent communication pretraining for both natural language processing tasks in resource-poor settings and extrinsic evaluation of artificial languages.