SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2011.00890 · 2020

Emergent Communication Pretraining for Few-Shot Machine Translation

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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\%$$\sim$$147.6\%$ in BLEU score with only $500$ NMT training instances and $65.1\%$$\sim$$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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2011.00890")
get_code_for_paper("2011.00890")
have("2011.00890")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2011.00890.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2011.00890.svg)](https://syntology.ai/paper/2011.00890)

Connect an agent — have() is free.