• DOI:10.18653/v1/W18-5454
Corpus ID: 53577360

Exploiting Attention to Reveal Shortcomings in Memory Models

@inproceedings{Burns2018ExploitingAT,
  title={Exploiting Attention to Reveal Shortcomings in Memory Models},
  author={Kaylee Burns and A. Nematzadeh and E. Grant and A. Gopnik and T. Griffiths},
  booktitle={BlackboxNLP@EMNLP},
  year={2018}
}

Kaylee Burns, A. Nematzadeh, +2 authors T. Griffiths

Published in BlackboxNLP@EMNLP 2018

Computer Science

The decision making processes of deep networks are difficult to understand and while their accuracy often improves with increased architectural complexity, so too does their opacity. Practical use of machine learning models, especially for question and answering applications, demands a system that is interpretable. We analyze the attention of a memory network model to reconcile contradictory performance on a challenging question-answering dataset that is inspired by theory-of-mind experiments… CONTINUE READING

View PDF

Save to Library

Create Alert

Cite

Launch Research Feed