F-Score Driven Max Margin Neural Network for Named Entity Recognition in Chinese Social Media
F-Score Driven Max Margin Neural Network for Named Entity Recognition in Chinese Social Media
复制标题
DOI：
10.18653/v1/e17-2113
复制
发表时间：
2016-11
期刊：
影响因子：
--
通讯作者：
Hangfeng He;Xu Sun
中科院分区：
文献类型：
--
作者：
Hangfeng He;Xu Sun
我们专注于中文社交媒体的命名实体识别（NER）。针对大量未标注文本和有限的标注语料，提出了一种基于B-LSTM神经网络的半监督学习模型。为了利用NER中的传统方法（如CRF），我们在模型中将联合收割机转移概率与深度学习相结合。为了弥补标注准确率和NER的F分数之间的差距，我们构建了一个可以直接在F分数上训练的模型。考虑到F-score驱动方法的不稳定性和标签准确度提供的有意义的信息，我们提出了一种综合的方法来训练F-score和标签准确度。我们的集成模型比以前的最先进的结果提高了7.44%。
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.