An Effective Label Noise Model for DNN Text Classification

Ishan Jindal, Daniel Pressel, Brian Lester, Matthew Nokleby


Abstract
Because large, human-annotated datasets suffer from labeling errors, it is crucial to be able to train deep neural networks in the presence of label noise. While training image classification models with label noise have received much attention, training text classification models have not. In this paper, we propose an approach to training deep networks that is robust to label noise. This approach introduces a non-linear processing layer (noise model) that models the statistics of the label noise into a convolutional neural network (CNN) architecture. The noise model and the CNN weights are learned jointly from noisy training data, which prevents the model from overfitting to erroneous labels. Through extensive experiments on several text classification datasets, we show that this approach enables the CNN to learn better sentence representations and is robust even to extreme label noise. We find that proper initialization and regularization of this noise model is critical. Further, by contrast to results focusing on large batch sizes for mitigating label noise for image classification, we find that altering the batch size does not have much effect on classification performance.
Anthology ID:
N19-1328
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Editors:
Jill Burstein, Christy Doran, Thamar Solorio
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3246–3256
Language:
URL:
https://aclanthology.org/N19-1328
DOI:
10.18653/v1/N19-1328
Bibkey:
Cite (ACL):
Ishan Jindal, Daniel Pressel, Brian Lester, and Matthew Nokleby. 2019. An Effective Label Noise Model for DNN Text Classification. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 3246–3256, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
An Effective Label Noise Model for DNN Text Classification (Jindal et al., NAACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/N19-1328.pdf
Data
AG News