ner and pos when nothing is capitalized

Stephen Mayhew, Tatiana Tsygankova, Dan Roth


Abstract
For those languages which use it, capitalization is an important signal for the fundamental NLP tasks of Named Entity Recognition (NER) and Part of Speech (POS) tagging. In fact, it is such a strong signal that model performance on these tasks drops sharply in common lowercased scenarios, such as noisy web text or machine translation outputs. In this work, we perform a systematic analysis of solutions to this problem, modifying only the casing of the train or test data using lowercasing and truecasing methods. While prior work and first impressions might suggest training a caseless model, or using a truecaser at test time, we show that the most effective strategy is a concatenation of cased and lowercased training data, producing a single model with high performance on both cased and uncased text. As shown in our experiments, this result holds across tasks and input representations. Finally, we show that our proposed solution gives an 8% F1 improvement in mention detection on noisy out-of-domain Twitter data.
Anthology ID:
D19-1650
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
6256–6261
Language:
URL:
https://aclanthology.org/D19-1650
DOI:
10.18653/v1/D19-1650
Bibkey:
Cite (ACL):
Stephen Mayhew, Tatiana Tsygankova, and Dan Roth. 2019. ner and pos when nothing is capitalized. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 6256–6261, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
ner and pos when nothing is capitalized (Mayhew et al., EMNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1650.pdf
Data
Broad Twitter CorpusCoNLL-2003Penn Treebank