Chinese named entity recognition method and device based on vocabulary enhancement and multiple features

Abstract

The invention discloses a Chinese named entity recognition method and device based on vocabulary enhancement and multiple features, and belongs to the technical field of information extraction. The method comprises the following steps: extracting character features of an input sequence in combination with a bidirectional long-short-term memory network and a convolutional neural network, introducing vocabulary information corresponding to characters in a character string mode matching manner, extracting vocabulary features in a word frequency weighted average manner, and extracting pre-training features by using a pre-training model; using a gating mechanism to control vocabulary enhancement of the vocabulary features to the character features; linearly splicing the character features subjected to vocabulary enhancement and the pre-training features to construct multiple features; obtaining context features based on context correlation of multiple features; and combining label decoding with context features to predict an optimal label sequence of the input sequence. Therefore, the character features of the Chinese sequence are extracted more fully; the extracted vocabulary features are richer, and the influence of Chinese word segmentation errors is avoided; and the entity identification index is improved by using a multi-feature combined strategy mode.

Description

technical field [0001] The invention belongs to the technical field of information extraction, and more specifically relates to a method and device for recognizing Chinese named entities based on vocabulary enhancement and multi-features. Background technique [0002] From the perspective of research, named entity recognition can be divided into two categories: one is based on traditional methods, mainly methods based on dictionaries and templates, methods based on unsupervised learning and supervised learning methods based on features; It is based on the deep learning method. According to the different input forms, this category can be summarized as word-level and word-level. [0003] The initial research methods were carried out by constructing lexical information and template rules. In most of these methods, industry experts manually constructed special dictionaries or templates based on the characteristics of the data set for matching and recognition. Generally speaking...

AI Technical Summary

Problems solved by technology

[0005] In view of the above defects or improvement needs of the prior art, the present invention proposes a Chinese named entity recognition method and device based on vocabulary enhancement and multi-features. Semantic information such as features, lexical features corresponding to characters, and pre-trained features lead to low recognition accuracy and recall

Images