End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF

TL;DR

This paper presents an end-to-end neural network architecture combining Bi-LSTM, CNN, and CRF for sequence labeling tasks, eliminating the need for feature engineering and pre-processing.

Contribution

The proposed model automatically learns both word- and character-level features, achieving state-of-the-art results on POS tagging and NER without manual feature design.

Findings

Achieved 97.55% accuracy on POS tagging

Attained 91.21% F1 score on NER

Outperformed previous models on both tasks

Abstract

State-of-the-art sequence labeling systems traditionally require large amounts of task-specific knowledge in the form of hand-crafted features and data pre-processing. In this paper, we introduce a novel neutral network architecture that benefits from both word- and character-level representations automatically, by using combination of bidirectional LSTM, CNN and CRF. Our system is truly end-to-end, requiring no feature engineering or data pre-processing, thus making it applicable to a wide range of sequence labeling tasks. We evaluate our system on two data sets for two sequence labeling tasks --- Penn Treebank WSJ corpus for part-of-speech (POS) tagging and CoNLL 2003 corpus for named entity recognition (NER). We obtain state-of-the-art performance on both the two data --- 97.55\% accuracy for POS tagging and 91.21\% F1 for NER.