Named entity recognition method and device for Chinese sentences

Abstract

The invention discloses a named entity recognition method for Chinese sentences, which comprises the following steps: inputting a Chinese character sequence into a recognition model, converting the Chinese character sequence into a character vector by the recognition model through a character embedding layer, and outputting the character vector to a convolutional network in the recognition model; the method also includes that the convolutional network performs convolution operation on each word vector to obtain a local semantic vector and outputs the local semantic vector to a self-adaptive combination layer in the recognition model; the self-adaptive combination layer performs attention calculation on the local semantic vector of the character and then splices the local semantic vector with the corresponding word vector to obtain a representation vector and outputs the representation vector to a sequence modeling network in the recognition model; and the sequence modeling network performs hidden layer modeling on the representation vector of the character and outputs the hidden layer vector obtained by modeling to a label reasoning layer in the recognition model to calculate a label corresponding to the hidden layer vector of the character. The local semantic information of the characters is extracted through the convolutional network and then is fused with the potential words based on the attention among the words, so that the utilization of the potential word information is realized, and the problem of wrong transmission of word boundaries is avoided.

Description

technical field [0001] The invention relates to the technical field of natural language processing, in particular to a method and device for recognizing named entities of Chinese sentences. Background technique [0002] The main task of named entity recognition is to identify entities with specific meaning in unstructured text, mainly including names of people, places, institutions and proper nouns. Together with word segmentation and dependency syntax analysis, it is the most important basic task in natural language processing tasks. It plays the role of cornerstone in many downstream tasks, and its recognition effect often largely determines the height that downstream tasks can achieve. Especially in information extraction tasks, it exists as a decisive basic task. [0003] Named entity recognition of Chinese sentences is an important sub-topic in the field of Chinese natural language processing. However, due to the diversity of Chinese expressions, the semantics of enti...

AI Technical Summary

Problems solved by technology

However, due to the diversity of Chinese expressions, the semantics of entities are usually highly related to contextual semantics, and due to the lack of separators for Chinese words in Chinese texts, word boundaries are blurred and difficult to judge, making the task of Chinese entity recognition very difficult.

In addition, since the mainstream entity recognition is based on sequence labeling, which makes the training set labeling cost very high, many entity recognition tasks have limited the performance of their models due to the lack of sufficient training sets. recognition effect

Images