Robustness to Capitalization Errors in Named Entity Recognition
This addresses robustness issues in named entity recognition for noisy user-generated text, though it is incremental as it builds on existing data augmentation methods.
The paper tackled the problem of named entity recognizers being brittle to capitalization errors, and the result was a data augmentation approach that achieved competitive robustness to such errors with negligible performance loss on well-formed text and improved generalization on noisy text.
Robustness to capitalization errors is a highly desirable characteristic of named entity recognizers, yet we find standard models for the task are surprisingly brittle to such noise. Existing methods to improve robustness to the noise completely discard given orthographic information, mwhich significantly degrades their performance on well-formed text. We propose a simple alternative approach based on data augmentation, which allows the model to \emph{learn} to utilize or ignore orthographic information depending on its usefulness in the context. It achieves competitive robustness to capitalization errors while making negligible compromise to its performance on well-formed text and significantly improving generalization power on noisy user-generated text. Our experiments clearly and consistently validate our claim across different types of machine learning models, languages, and dataset sizes.