# Attending to Characters in Neural Sequence Labeling Models

arXiv: https://arxiv.org/abs/1611.04361 · HTML: https://mlsanity.com/paper/1611.04361/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Nov 2016.

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

- [Incremental Sequence Labeling: A Tale of Two Shifts](https://mlsanity.com/paper/2402.10447/) (2024)
- [Neural Sequence-to-Sequence Modeling with Attention by Leveraging Deep Learning Architectures for Enhanced Contextual Understanding in Abstractive Text Summarization](https://mlsanity.com/paper/2404.08685/) (2024)
- [A Context-Enhanced De-identification System](https://mlsanity.com/paper/2102.08513/) (2021)
- [AsPOS: Assamese Part of Speech Tagger using Deep Learning Approach](https://mlsanity.com/paper/2212.07043/) (2022)
- [Part-of-Speech Tagger for Bodo Language using Deep Learning approach](https://mlsanity.com/paper/2401.03175/) (2024)
- [Software Entity Recognition with Noise-Robust Learning](https://mlsanity.com/paper/2308.10564/) (2023)
- [Dynamic Named Entity Recognition](https://mlsanity.com/paper/2302.10314/) (2023)
- [SpanRE: Entities and Overlapping Relations Extraction Based on Spans and Entity Attention](https://mlsanity.com/paper/2304.02901/) (2023)
- [Event prediction and causality inference despite incomplete information](https://mlsanity.com/paper/2406.05893/) (2024)
- [End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF: A Reproducibility Study](https://mlsanity.com/paper/2510.10936/) (2025)

## Abstract (arXiv)

Sequence labeling architectures use word embeddings for capturing similarity, but suffer when handling previously unseen or rare words. We investigate character-level extensions to such models and propose a novel architecture for combining alternative word representations. By using an attention mechanism, the model is able to dynamically decide how much information to use from a word- or character-level component. We evaluated different architectures on a range of sequence labeling datasets, and character-level extensions were found to improve performance on every benchmark. In addition, the proposed attention-based architecture delivered the best results even with a smaller number of trainable parameters.