Event trigger word extraction method based on document level attention mechanism

Abstract

The invention relates to an event trigger word extraction method, in particular to an event trigger word extraction method based on a document level attention mechanism, comprising the following steps: (1) preprocessing training corpus; (2) performing word vector training by using PubMed database corpus; (3) constructing a distributed representation way of a sample; (4) constructing a characteristic representation way based on BiLSTM-Attention; (5) adopting CRF learning, and acquiring an optimal sequence labeling result of the current document sequence; and (6) extracting event trigger words.The method provided by the invention has the advantages that firstly a BIO tag labeling way is adopted, and recognition including multi-word trigger word recognition is realized; secondly a corresponding simple word and characteristic distributed representation way is constructed for a trigger word recognition task; and thirdly, a BiLSTM-Attention model is proposed, a distributed representation structure specific to the currently input document level information is realized by introducing an Attention mechanism, and trigger word recognition effect is improved.

Description

technical field [0001] The present invention relates to a method for extracting event-triggered words, and more specifically, relates to a method for extracting event-triggered words based on a document-level attention mechanism. Background technique [0002] As a form of information extraction, event extraction aims to extract structured event information from natural language text. An event usually consists of a trigger word or phrase (Trigger) and several event elements (Argument). Trigger words are usually verbs or nouns with the nature of verbs, which are used to indicate the type of event. Then around the trigger words, the participating elements of the event, the event elements, are identified. Trigger word recognition is a key step in event extraction, and the recognition performance directly determines the accuracy of event extraction. [0003] In the past, the recognition of trigger words was regarded as a multi-classification task, and the candidate words in th...

AI Technical Summary

Problems solved by technology

However, the events involved in a document are often related, and there is a phenomenon of event types clustering in the document

There is a way to use the topic model to introduce chapter-level features, but for the candidate words of the same document, this article-level feature is not specific to the candidate trigger words of the same document, and cannot be targeted to obtain the current candidate words. Chapter Level Information

Images