Neural Speed Reading Audited

Anders Søgaard


Abstract
Several approaches to neural speed reading have been presented at major NLP and machine learning conferences in 2017–20; i.e., “human-inspired” recurrent network architectures that learn to “read” text faster by skipping irrelevant words, typically optimizing the joint objective of minimizing classification error rate and FLOPs used at inference time. This paper reflects on the meaningfulness of the speed reading task, showing that (a) better and faster approaches to, say, document classification, already exist, which also learn to ignore part of the input (I give an example with 7% error reduction and a 136x speed-up over the state of the art in neural speed reading); and that (b) any claims that neural speed reading is “human-inspired”, are ill-founded.
Anthology ID:
2020.findings-emnlp.14
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2020
Month:
November
Year:
2020
Address:
Online
Editors:
Trevor Cohn, Yulan He, Yang Liu
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
148–153
Language:
URL:
https://aclanthology.org/2020.findings-emnlp.14
DOI:
10.18653/v1/2020.findings-emnlp.14
Bibkey:
Cite (ACL):
Anders Søgaard. 2020. Neural Speed Reading Audited. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 148–153, Online. Association for Computational Linguistics.
Cite (Informal):
Neural Speed Reading Audited (Søgaard, Findings 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.findings-emnlp.14.pdf