Construction method, device, electronic device and storage medium of event detection model

Abstract

An embodiment of the present invention provides a method, device, electronic device, and storage medium for constructing a deep learning model for event detection based on open domain knowledge enhancement. The method includes: acquiring labeled data and unlabeled data; inputting the labeled data into the first event In the classification model, training is carried out; according to the external semantic library, the sememe mapping algorithm is used to process the first data subset in the unlabeled data, and the recognition result of the open-domain trigger word is obtained; according to the recognition result of the open-domain trigger word and the second data The subset uses knowledge distillation to train the second event classification model; jointly trains the trained first event classification model and the trained second event classification model to obtain event detection depth based on open domain knowledge enhancement learning model. The event detection deep learning model based on open domain knowledge enhancement obtained in the embodiment of the present invention can effectively solve the long-tail problem of uneven distribution of various labels.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a construction method, device, electronic equipment and storage medium of an event detection deep learning model based on open domain knowledge enhancement. Background technique [0002] Event detection aims to discover events from unstructured news reports. At present, event detection, as a basic core technology in the field of artificial intelligence, has been widely introduced into reading comprehension and text summarization tasks. [0003] The event detection task is divided into two steps, the first step detects trigger words in sentences, and the second step classifies trigger words into predefined event types. Most of the existing work focuses on the second step of event type classification, such as proposing models such as dynamic convolutional networks and hierarchical attention mechanisms. However, trigger word recognition is also very critical. There is a ...

AI Technical Summary

Problems solved by technology

For the long-tail problem, if a supervised method is used to rely only on labeled corpus for training, it is easy to overfit and perform poorly on triggers that do not appear / label sparsely; if a self-iterative method is used to expand training examples based on pseudo-labels, then Due to the uneven distribution of the seed set data itself, the expanded data set is also concentrated on multi-labeled trigger words, which cannot alleviate the long-tail problem; if the remote supervision method is used to expand more data by relying on an external knowledge base, it is limited by the knowledge base The problem of its own field limitations and low coverage cannot alleviate the long tail problem

Images