Abstract
We compare the use of LSTM-based and CNN-based character-level word embeddings in BiLSTM-CRF models to approach chemical and disease named entity recognition (NER) tasks. Empirical results over the BioCreative V CDR corpus show that the use of either type of character-level word embeddings in conjunction with the BiLSTM-CRF models leads to comparable state-of-the-art performance. However, the models using CNN-based character-level word embeddings have a computational performance advantage, increasing training time over word-based models by 25% while the LSTM-based character-level word embeddings more than double the required training time.
Abstract (translated)
我们比较了在BiLSTM-CRF模型中使用基于LSTM和基于CNN的字符级字嵌入来接近化学和疾病命名实体识别(NER)任务。 BioCreative V CDR语料库的实证结果表明,将任一类型的字符级字嵌入与BiLSTM-CRF模型结合使用,可以获得与现有技术相媲美的性能。然而,使用基于CNN的字符级字嵌入的模型具有计算性能优势,比基于字的模型增加了25%的训练时间,而基于LSTM的字符级字嵌入则超过所需训练时间的两倍。
URL
https://arxiv.org/abs/1808.08450