F-Score Driven Max Margin Neural Network for Named Entity Recognition in Chinese Social Media
This addresses the problem of limited labeled data for NER in Chinese social media, offering an incremental improvement over existing methods.
The paper tackles named entity recognition in Chinese social media by proposing a semi-supervised model that integrates B-LSTM with CRF and trains directly on F-score and label accuracy, achieving a 7.44% improvement over previous state-of-the-art results.
We focus on named entity recognition (NER) for Chinese social media. With massive unlabeled text and quite limited labelled corpus, we propose a semi-supervised learning model based on B-LSTM neural network. To take advantage of traditional methods in NER such as CRF, we combine transition probability with deep learning in our model. To bridge the gap between label accuracy and F-score of NER, we construct a model which can be directly trained on F-score. When considering the instability of F-score driven method and meaningful information provided by label accuracy, we propose an integrated method to train on both F-score and label accuracy. Our integrated model yields 7.44\% improvement over previous state-of-the-art result.