Character-Level Feature Extraction with Densely Connected Networks
This addresses the need for efficient and robust character-level feature extraction in NLP, offering improvements over existing methods like CNN and RNN, though it is incremental in nature.
The paper tackles the problem of automatically extracting character-level features for NLP tasks by proposing a densely connected network method, which achieves state-of-the-art performance with 96.62 F1-score on slot tagging and 97.73% accuracy on POS tagging, and comparable 91.13 F1-score on NER.
Generating character-level features is an important step for achieving good results in various natural language processing tasks. To alleviate the need for human labor in generating hand-crafted features, methods that utilize neural architectures such as Convolutional Neural Network (CNN) or Recurrent Neural Network (RNN) to automatically extract such features have been proposed and have shown great results. However, CNN generates position-independent features, and RNN is slow since it needs to process the characters sequentially. In this paper, we propose a novel method of using a densely connected network to automatically extract character-level features. The proposed method does not require any language or task specific assumptions, and shows robustness and effectiveness while being faster than CNN- or RNN-based methods. Evaluating this method on three sequence labeling tasks - slot tagging, Part-of-Speech (POS) tagging, and Named-Entity Recognition (NER) - we obtain state-of-the-art performance with a 96.62 F1-score and 97.73% accuracy on slot tagging and POS tagging, respectively, and comparable performance to the state-of-the-art 91.13 F1-score on NER.