AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Robust Named Entity Recognition with Truecasing Pretraining

Stephen Mayhew, Gupta Nitish, Dan Roth

AAAI 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 36 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add pretrained truecaser representations to cased-trained BiLSTM-CRF+GloVeBiLSTM-CRF+GloVe uncased · CoNLL2003 test, uncasedF1: 24.3 -> 84.5Improved
Add pretrained truecaser representations to cased-trained BiLSTM-CRF+GloVeBiLSTM-CRF+GloVe uncased · Ontonotes test, uncasedF1: 83.5 -> 81.1Hurt
Add pretrained truecaser representations to cased-trained BiLSTM-CRF+GloVeBiLSTM-CRF+GloVe uncased · WNUT17 test, uncasedF1: 15.7 -> 30.2Improved
Add pretrained truecaser representations to uncased-trained GloVe NERBiLSTM-CRF+GloVe uncased · CoNLL test, uncasedF1: 87.3 -> 88.3Improved
Add pretrained truecaser representations to uncased-trained GloVe NERBiLSTM-CRF+GloVe uncased · Ontonotes test, uncasedF1: 83.4 -> 84.4Improved
Add pretrained truecaser representations to uncased-trained GloVe NERBiLSTM-CRF+GloVe uncased · WNUT17 test, uncasedF1: 41.1 -> 43.2Improved
Add pretrained truecaser representations to uncased BERT NERBERT uncased · CoNLL test, uncasedF1: 91.0 -> 91.2Improved
Add pretrained truecaser representations to uncased BERT NERBERT uncased · Ontonotes test, uncasedF1: 88.1 -> 88.1No clear effect
Add pretrained truecaser representations to uncased BERT NERBERT uncased · WNUT17 test, uncasedF1: 46.1 -> 46.9Improved
Initialize the truecaser on CoNLL training data instead of Common Crawl (ablation)BiLSTM-CRF+GloVe · CoNLL2003 testb, uncasedNER F1: 88.3 -> 85.3Hurt
Fine-tune a pretrained truecaser (ablation)BERT uncased NER · WNUT17 test, uncasedNER F1: 46.9 -> 46.3Hurt
Fine-tune a pretrained truecaser (ablation)BERT uncased NER · WNUT17 test, uncasedChar F1: 30.6 -> 52.3Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy