Biomedical event trigger word identification method based on syntactic word vector

Abstract

The invention relates to an identification method, in particular to a biomedical event trigger word identification method based on a syntactic word vector. The biomedical event trigger word identification method comprises the following steps of: 1, pre-processing un-marked data; 2, carrying out word vector training based on syntactic context information; 3, constructing a candidate trigger word dictionary; 4, constructing a trigger word semantic feature vector; 5, training a deep learning model; and 6, identifying a biomedical event trigger word. According to the biomedical event trigger word identification method, syntactic information of the trigger word is precisely acquired by utilizing a larger number of trained word vectors capable of obtaining unmarked data, and input characteristic dimension is effectively reduced; concealed features among the input features are leaned by utilizing the deep learning model, so that the input features are sorted more precisely; and finally, fine adjustment is carried out on word vector information in a training process, so that the word vector information is more suitable for a data set, and thus, the generalization ability and the trigger word identification word of the model are effectively improved.

Description

technical field [0001] The present invention relates to a recognition method, more specifically, relates to a biomedical event trigger word recognition method based on a syntactic word vector. Background technique [0002] With the rapid development of systems biology, the need to reveal the complex relationships among biomolecules, cells, and tissues is becoming more and more urgent. At the same time, the published biomedical literature is also showing explosive growth. How to mine complex relationships among biomolecules, cells, tissues, etc. from a large number of biomedical literatures instead of traditional simple binary relationships (such as protein -protein relationship, drug-drug relationship, etc.) has become a research hotspot in the field of modern biomedical text mining. [0003] At present, most biomedical event extraction methods divide this task into two subtasks: trigger word recognition and element detection, and trigger word recognition plays a decisive r...

AI Technical Summary

Problems solved by technology

This method is obviously better than the method based on rule matching, and has been widely used, but there are still some shortcomings, it is more dependent on the labeled data, when the labeled data is relatively small, its performance cannot be guaranteed; moreover, the construction of features is mainly for The current data set is manually constructed, the manual intervention is relatively large, the generalization performance is not good, the manually constructed feature vector has a high dimension and is sparse, and the training is time-consuming

Images