Recognizing irregular entities in biomedical text via deep neural networks

论文链接：https://www.sciencedirect.com/science/article/pii/S0167865517302155#fig0001

代码链接：https://github.com/foxlf823/nodner

知乎笔记：https://zhuanlan.zhihu.com/p/47498650

Highlights

•Novel models are proposed for recognizing discontinuous and overlapped entities.

•The models are based on bidirectional LSTMs and CRFs.

•The models require little feature engineering.

•Results are competitive compared with state-of-the-art systems.

Abstract

Named entity recognition (NER) is an important task for biomedical text mining. Most prior work focused on recognizing regular entities that consist of continuous word sequences and are not overlapped with each other. In this paper, we propose a neural network model called Bi-LSTM-CRF that consists of bidirectional (Bi) long short-term memories (LSTMs) and conditional random fields (CRFs) to identify regular entities and the components of irregular entities. Then the components are combined to build final irregular entities according to manually designed rules. Furthermore, we propose a novel model called NerOne that consists of the Bi-LSTM-CRF network and another Bi-LSTM network. The Bi-LSTM-CRF network performs the same task as the aforementioned model, and the Bi-LSTM network determines whether two components should be combined. Therefore, NerOne automatically combines the components instead of using manually designed rules. We evaluate our models on two datasets for recognizing regular and irregular biomedical entities. Experimental results show that, with less feature engineering, the performances of our models are comparable with those of state-of-the-art systems. We show that the method of automatically combining the components is as effective as the method of manually designing rules. Our work can facilitate the research on biomedical text mining.

Model architecture

解码的目的是找到所有完整的子图G'，其中每对不同的顶点之间通过唯一的边缘相连。 最后，完整子图中的所有组件都构成一个集成的不规则实体。

备注：

论文提到在解码的部分：“解码的目的是找到所有完整的子图G'，其中每对不同的顶点之间通过唯一的边缘相连。 最后，完整子图中的所有组件都构成一个集成的不规则实体。”

您的笔记中提到“如果存在组合关系，则在两个词间加上边，最后通过查看词连接图里的最大全连接子图提取出来作为实体的词序列”

请问在通过最大全连接子图提取实体词序列过程中，如何确定词之间的顺序哪？