Boring Problems Are Sometimes the Most Interesting
Open Access
- 9 June 2022
- journal article
- research article
- Published by MIT Press in Computational Linguistics
- Vol. 48 (2) , 483-490
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.Keywords
This publication has 19 references indexed in Scilit:
- Text normalization with convolutional neural networksInternational Journal of Speech Technology, 2018
- A Mostly Data-Driven Approach to Inverse Text Normalization2017
- An RNN Model of Text Normalization2017
- CoNLL-SIGMORPHON 2017 Shared Task: Universal Morphological Reinflection in 52 Languages2017
- Incorporating Discrete Translation Lexicons into Neural Machine Translation2016
- NCSU_SAS_WOOKHEE: A Deep Contextual Long-Short Term Memory Model for Text Normalization2015
- The Kestrel TTS text normalization systemNatural Language Engineering, 2014
- Toward text message normalization: Modeling abbreviation generation2011
- Normalizing SMS2008
- Normalization of non-standard wordsComputer Speech & Language, 2001