Neural Speed Reading Audited
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
Neural Speed Reading Audited. / Søgaard, Anders.
Findings of the Association for Computational Linguistics: EMNLP 2020. Association for Computational Linguistics, 2020. p. 148–153.Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Neural Speed Reading Audited
AU - Søgaard, Anders
PY - 2020
Y1 - 2020
N2 - 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.
AB - 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.
U2 - 10.18653/v1/2020.findings-emnlp.14
DO - 10.18653/v1/2020.findings-emnlp.14
M3 - Article in proceedings
SP - 148
EP - 153
BT - Findings of the Association for Computational Linguistics: EMNLP 2020
PB - Association for Computational Linguistics
T2 - The 2020 Conference on Empirical Methods in Natural Language Processing
Y2 - 16 November 2020 through 20 November 2020
ER -
ID: 258378396