Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Boring Problems Are Sometimes the Most Interesting

Boring Problems Are Sometimes the Most Interesting In a recent position paper, Turing Award Winners Yoshua Bengio, Geoffrey Hinton, and Yann LeCun make the case that symbolic methods are not needed in AI and that, while there are still many issues to be resolved, AI will be solved using purely neural methods. In this piece I issue a challenge: Demonstrate that a purely neural approach to the problem of text normalization is possible. Various groups have tried, but so far nobody has eliminated the problem of unrecoverable errors, errors where, due to insufficient training data or faulty generalization, the system substitutes some other reading for the correct one. Solutions have been proposed that involve a marriage of traditional finite-state methods with neural models, but thus far nobody has shown that the problem can be solved using neural methods alone. Though text normalization is hardly an “exciting” problem, I argue that until one can solve “boring” problems like that using purely AI methods, one cannot claim that AI is a success. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Computational Linguistics MIT Press

Boring Problems Are Sometimes the Most Interesting

Sproat, Richard
Computational Linguistics , Volume 48 (2): 8 – Jun 9, 2022
Download PDF
8 pages

Loading next page...
 
/lp/mit-press/boring-problems-are-sometimes-the-most-interesting-2KJZQybVre

References (45)

Publisher
MIT Press
Copyright
© 2022 Association for Computational Linguistics. Published under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) license.
ISSN
0891-2017
eISSN
1530-9312
DOI
10.1162/coli_a_00439
Publisher site
See Article on Publisher Site

Abstract

In a recent position paper, Turing Award Winners Yoshua Bengio, Geoffrey Hinton, and Yann LeCun make the case that symbolic methods are not needed in AI and that, while there are still many issues to be resolved, AI will be solved using purely neural methods. In this piece I issue a challenge: Demonstrate that a purely neural approach to the problem of text normalization is possible. Various groups have tried, but so far nobody has eliminated the problem of unrecoverable errors, errors where, due to insufficient training data or faulty generalization, the system substitutes some other reading for the correct one. Solutions have been proposed that involve a marriage of traditional finite-state methods with neural models, but thus far nobody has shown that the problem can be solved using neural methods alone. Though text normalization is hardly an “exciting” problem, I argue that until one can solve “boring” problems like that using purely AI methods, one cannot claim that AI is a success.

Journal

Computational Linguistics – MIT Press

Published: Jun 9, 2022

There are no references for this article.