Multi-channel BiLSTM-CRF Model for Emerging Named Entity Recognition in Social Media

Citations Over TimeTop 10% of 2017 papers

Abstract

In this paper, we present our multichannel neural architecture for recognizing emerging named entity in social media messages, which we applied in the Novel and Emerging Named Entity Recognition shared task at the EMNLP 2017 Workshop on Noisy User-generated Text (W-NUT). We propose a novel approach, which incorporates comprehensive word representations with multichannel information and Conditional Random Fields (CRF) into a traditional Bidirectional Long Short-Term Memory (BiL-STM) neural network without using any additional hand-crafted features such as gazetteers. In comparison with other systems participating in the shared task, our system won the 3rd place in terms of the average of two evaluation metrics.

Related Papers

• → Randomized Kernel Approach for Named Entity Recognition in Tamil(2015)12 cited
• → Biomedical Named Entity Recognition Based on Skip-Chain CRFS(2012)22 cited
• Chinese Word Segmentation and Named Entity Recognition Based on Conditional Random Fields Models(2006)
• Two Step Chinese Named Entity Recognition Based on Conditional Random Fields Models(2008)
• → Conditional Random Fields for Biomedical Named Entity Recognition Revisited(2020)