A Multi-task Approach for Named Entity Recognition in Social Media Data
This work addresses the problem of extracting named entities from noisy social media text for NLP applications, representing an incremental improvement over existing methods.
The paper tackled the challenge of Named Entity Recognition in noisy social media data by proposing a multi-task neural network that combines NE segmentation with fine-grained categorization, achieving first place in the WNUT-2017 workshop with a 41.86% entity F1-score and a 40.24% surface F1-score.
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.