# ner and pos when nothing is capitalized

arXiv: https://arxiv.org/abs/1903.11222 · HTML: https://mlsanity.com/paper/1903.11222/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Mar 2019.

## Built on by (most cited first, 15 of 15)

- [MasakhaNER 2.0: Africa-centric Transfer Learning for Named Entity Recognition](https://mlsanity.com/paper/2210.12391/) (2022)
- [Context-aware Adversarial Training for Name Regularity Bias in Named Entity Recognition](https://mlsanity.com/paper/2107.11610/) (2021)
- [MultiCoNER: A Large-scale Multilingual dataset for Complex Named Entity Recognition](https://mlsanity.com/paper/2208.14536/) (2022)
- [SemEval-2023 Task 2: Fine-grained Multilingual Named Entity Recognition (MultiCoNER 2)](https://mlsanity.com/paper/2305.06586/) (2023)
- [Capitalization and Punctuation Restoration: a Survey](https://mlsanity.com/paper/2111.10746/) (2021)
- [ACLM: A Selective-Denoising based Generative Data Augmentation Approach for Low-Resource Complex NER](https://mlsanity.com/paper/2306.00928/) (2023)
- [An Effective, Performant Named Entity Recognition System for Noisy Business Telephone Conversation Transcripts](https://mlsanity.com/paper/2209.13736/) (2022)
- [Improving Named Entity Recognition in Telephone Conversations via Effective Active Learning with Human in the Loop](https://mlsanity.com/paper/2211.01354/) (2022)
- [Cross-Lingual Transfer from Related Languages: Treating Low-Resource Maltese as Multilingual Code-Switching](https://mlsanity.com/paper/2401.16895/) (2024)
- [MultiCoNER v2: a Large Multilingual dataset for Fine-grained and Noisy Named Entity Recognition](https://mlsanity.com/paper/2310.13213/) (2023)
- [Re-Evaluating GermEval17 Using German Pre-Trained Language Models](https://mlsanity.com/paper/2102.12330/) (2021)
- [Automatic Construction of Enterprise Knowledge Base](https://mlsanity.com/paper/2106.15085/) (2021)
- [UM6P-CS at SemEval-2022 Task 11: Enhancing Multilingual and Code-Mixed Complex Named Entity Recognition via Pseudo Labels using Multilingual Transformer](https://mlsanity.com/paper/2204.13515/) (2022)
- [reproducing "ner and pos when nothing is capitalized"](https://mlsanity.com/paper/2109.08396/) (2021)
- [Towards a Diagnostic and Predictive Evaluation Methodology for Sequence Labeling Tasks](https://mlsanity.com/paper/2602.12759/) (2026)

## Abstract (arXiv)

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.