• DOI:10.18653/v1/W19-4801
Corpus ID: 174797793

Transcoding compositionally: using attention to find more generalizable solutions

@article{Korrel2019TranscodingCU,
  title={Transcoding compositionally: using attention to find more generalizable solutions},
  author={K. Korrel and Dieuwke Hupkes and Verna Dankers and Elia Bruni},
  journal={ArXiv},
  year={2019},
  volume={abs/1906.01234}
}

K. Korrel, Dieuwke Hupkes, +1 author Elia Bruni

Published 2019

Computer Science

ArXiv

While sequence-to-sequence models have shown remarkable generalization power across several natural language tasks, their construct of solutions are argued to be less compositional than human-like generalization. In this paper, we present seq2attn, a new architecture that is specifically designed to exploit attention to find compositional patterns in the input. In seq2attn, the two standard components of an encoder-decoder model are connected via a transcoder, that modulates the information… CONTINUE READING

View on ACL

arxiv.org

Save to Library

Create Alert

Cite

Launch Research Feed