reproducing "ner and pos when nothing is capitalized"

원문 초록

Capitalization is an important feature in many NLP tasks such as Named Entity Recognition (NER) or Part of Speech Tagging (POS). We are trying to reproduce results of paper which shows how to mitigate a significant performance drop when casing is mismatched between training and testing data. In particular we show that lowercasing 50% of the dataset provides the best performance, matching the claims of the original paper. We also show that we got slightly lower performance in almost all experiments we have tried to reproduce, suggesting that there might be some hidden factors impacting our performance. Lastly, we make all of our work available in a public github repository.