| 2 |
Emergent Communication Pretraining for Few-Shot Machine Translation ...
|
|
|
|
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 \textit{ex vitro}. Intuitively, the closer they are to natural languages, the higher the gains from pretraining on them should be. For ...
|
|
Keyword:
Computer and Information Science; Natural Language Processing; Neural Network
|
|
URL: https://underline.io/lecture/6290-emergent-communication-pretraining-for-few-shot-machine-translation
https://dx.doi.org/10.48448/13e8-dh54
|
|
BASE
|
|
Hide details
|
|
|
| 3 |
Manual Clustering and Spatial Arrangement of Verbs for Multilingual Evaluation and Typology Analysis ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 4 |
SemEval-2020 Task 2: Predicting Multilingual and Cross-Lingual (Graded) Lexical Entailment ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 5 |
Specializing Unsupervised Pretraining Models for Word-Level Semantic Similarity ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|
|
