# Boosting Named Entity Recognition with Neural Character Embeddings

arXiv: https://arxiv.org/abs/1505.05008 · HTML: https://mlsanity.com/paper/1505.05008/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 May 2015.

## Built on by (most cited first, 10 of 10)

- [Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI](https://mlsanity.com/paper/2111.06061/) (2021)
- [Cross-Task Instance Representation Interactions and Label Dependencies for Joint Information Extraction with Graph Convolutional Networks](https://mlsanity.com/paper/2103.09330/) (2021)
- [MetaIE: Distilling a Meta Model from LLM for All Kinds of Information Extraction Tasks](https://mlsanity.com/paper/2404.00457/) (2024)
- [Recent Trends in Named Entity Recognition (NER)](https://mlsanity.com/paper/2101.11420/) (2021)
- [Regularization for Long Named Entity Recognition](https://mlsanity.com/paper/2104.07249/) (2021)
- [NERDA-Con: Extending NER models for Continual Learning -- Integrating Distinct Tasks and Updating Distribution Shifts](https://mlsanity.com/paper/2206.14607/) (2022)
- [SciEv: Finding Scientific Evidence Papers for Scientific News](https://mlsanity.com/paper/2205.00126/) (2022)
- [A character representation enhanced on-device Intent Classification](https://mlsanity.com/paper/2101.04456/) (2021)
- [KARL-Trans-NER: Knowledge Aware Representation Learning for Named Entity Recognition using Transformers](https://mlsanity.com/paper/2111.15436/) (2021)
- [#maskUp: Selective Attribute Encryption for Sensitive Vocalization for English language on Social Media Platforms](https://mlsanity.com/paper/2211.08653/) (2022)

## Abstract (arXiv)

Most state-of-the-art named entity recognition (NER) systems rely on handcrafted features and on the output of other NLP tasks such as part-of-speech (POS) tagging and text chunking. In this work we propose a language-independent NER system that uses automatically learned features only. Our approach is based on the CharWNN deep neural network, which uses word-level and character-level representations (embeddings) to perform sequential classification. We perform an extensive number of experiments using two annotated corpora in two different languages: HAREM I corpus, which contains texts in Portuguese; and the SPA CoNLL-2002 corpus, which contains texts in Spanish. Our experimental results shade light on the contribution of neural character embeddings for NER. Moreover, we demonstrate that the same neural network which has been successfully applied to POS tagging can also achieve state-of-the-art results for language-independet NER, using the same hyperparameters, and without any handcrafted features. For the HAREM I corpus, CharWNN outperforms the state-of-the-art system by 7.9 points in the F1-score for the total scenario (ten NE classes), and by 7.2 points in the F1 for the selective scenario (five NE classes).