Biological event extracting method based on candidate event element attention mechanism

Abstract

The invention relates to a biological event extracting method, in particular to a biological event extracting method based on a candidate event element attention mechanism. The method includes the following steps that (1), a training corpus is pre-processed; (2), a PubMed database corpus is used for word vector training; (3), a distributed expression mode of sequences is established; (4), a feature expression mode based on BiLST-Attention is established; (5), an optimal sequence labeling result of a current document sequence is acquired through CRF learning; (6), biological events are extracted. The method has the following advantages that event element recognition aiming at trigger words is carried out in a sequence labeling mode, and multiple event elements can be recognized for one trigger word; an Attention layer aiming at candidate event elements is established, and compared with a traditional sequence labeling method, attention weights of the candidate event elements can be increased; the steps of generating events are simplified.

Description

technical field [0001] The present invention relates to a biological event extraction method, more specifically, to a biological event extraction method based on candidate event element attention mechanism. Background technique [0002] In the field of bioinformatics, an event refers to a change in the state of one or more biomedical entities (eg, proteins, cells, and chemicals). These changes are of great significance for understanding biological processes and functions, as well as for in-depth understanding of physiology and pathogenesis. Automatically creating structured representations of these textual descriptions can not only construct biological networks composed of such events in information retrieval and question answering systems, but can also be used in knowledge discovery, finding new associations between biological entities. [0003] The biological event extraction task aims to obtain biological event information from text and represent it in a structured manne...

AI Technical Summary

Problems solved by technology

For events containing multiple elements and nesting (such as regulation and binding events), there are often associations between event elements, and the way of considering binary relationship pairs alone cannot effectively utilize the mutual information between event elements

Finally, for multi-element events, post-processing is required to generate multi-element events based on binary relationship classification. Different post-processing methods will also affect the results of event extraction.

Images