Biomedical Event Extraction as Semantic Segmentation

In the biomedical field, information is widely distributed across numerous pieces of literature. Extracting events between entities from biomedical texts has garnered significant attention in recent years. However, previous research primarily focus on extracting flat biomedical events, with less attention given to nested biomedical events. Moreover, existing methods for extracting nested events often overlook the long-distance dependencies and global information between trigger words and arguments within events, and they lack sufficient interaction with event type information. To address these issues, we propose a semantic segmentation-based method for extracting nested biomedical events. We introduce U-Net to capture global information and interdependencies between event entities. Additionally, we map event types to natural language text and combine them with sentences for encoding to enhance interaction. We also employ two auxiliary tasks to improve the identification of trigger words and arguments. Finally, events are extracted by identifying the four vertices of the segmented region. Experimental results on two benchmark datasets show that our method excels in recognizing nested biomedical events and outperforms current state-of-the-art methods.

I. Introduction

In the biomedical field, information is spread across a lot of literature. Using Natural Language Processing (NLP) techniques to extract this information has been a key research focus. One of the most important tasks is extracting events between entities from biomedical texts. Usually, an event is made up of a trigger word and arguments that define the event’s structure. The event trigger word is a keyword that shows an event is happening. It is also important for figuring out the event’s category and subcategory. The arguments describe the event in more detail, including the different roles involved.