# A Multi-task Approach for Named Entity Recognition in Social Media Data

## TL;DR

This paper introduces a multi-task neural network approach for improving Named Entity Recognition in noisy social media text by jointly learning entity segmentation and categorization, achieving top performance in a competitive benchmark.

## Contribution

It presents a novel multi-task neural architecture that combines entity segmentation and categorization, enhancing feature learning for social media NER tasks.

## Key findings

- Achieved 41.86% entity F1-score on WNUT-2017.
- First place in the 3rd Workshop on Noisy User-generated Text.
- Effective use of multi-task learning for noisy text NER.

## Abstract

Named Entity Recognition for social media data is challenging because of its inherent noisiness. In addition to improper grammatical structures, it contains spelling inconsistencies and numerous informal abbreviations. We propose a novel multi-task approach by employing a more general secondary task of Named Entity (NE) segmentation together with the primary task of fine-grained NE categorization. The multi-task neural network architecture learns higher order feature representations from word and character sequences along with basic Part-of-Speech tags and gazetteer information. This neural network acts as a feature extractor to feed a Conditional Random Fields classifier. We were able to obtain the first position in the 3rd Workshop on Noisy User-generated Text (WNUT-2017) with a 41.86% entity F1-score and a 40.24% surface F1-score.