Probing RNN Encoder-Decoder Generalization of Subregular Functions using Reduplication

Published in Proceedings of the Society for Computation in Linguistics, 2020

Max Nelson, Hossep Dolatian, Jonathan Rawski, and Brandon Prickett

This paper examines the generalization abilities of encoder-decoder networks on a class of subregular functions characteristic of natural language reduplication. We find that, for the simulations we run, attention is a necessary and sufficient mechanism for learning generalizable reduplication. We examine attention alignment to connect RNN computation to a class of 2-way transducers.

Download paper here

Code available here