Method and device for name disambiguation

Abstract

The invention provides a name disambiguation method and apparatus. The method comprises the following steps: preprocessing full-text information of names to be disambiguated so as to extract semantic features of the full-text information; according to the semantic features, generating semantic fingerprints of the full-text information of the names to be disambiguated, including mail fingerprints, coauthor fingerprints, mechanism fingerprints and text fingerprints; through comparing the full-text information of the names to be disambiguated with semantic fingerprints having same-name full-text information as the names to be disambiguated in a preset semantic fingerprint database, determining similarity between the full-text information of the names to be disambiguated and the semantic fingerprints having the same-name full-text information as the names to be disambiguated in the preset semantic fingerprint database; and according to the semantic fingerprint similarity, determining a name group after disambiguation which the semantic fingerprints of the full-text information of the names to be disambiguated belongs to. By using such a method, while name disambiguation accuracy is ensured, the name disambiguation speed is improved, and increment name disambiguation is supported.

Description

technical field [0001] The present invention relates to the field of entity disambiguation, in particular, the present invention relates to a name disambiguation method and device. Background technique [0002] In recent years, with the development of computer technology and the popularization and application of the Internet, more and more information is available on the Internet. The rapid growth of information makes us obtain rich information content, but also creates the problem of how to quickly obtain the information we need. As users' demand for high-quality search continues to increase, and people's information search is also growing. Users hope to obtain the basic information of the person they want to know through search. Due to the common phenomenon of the same name, the name is often highly ambiguous, and the quality of the current search results is not satisfactory. So it becomes more difficult to obtain information about a specific person. And name disambigua...

AI Technical Summary

Problems solved by technology

The process of traditional name disambiguation in the field of entity disambiguation includes: feature collection and selection, clustering algorithm; in the feature selection stage, it is necessary to combine Internet knowledge resources to extract more character entity features, or construct the name to be disambiguated Social network; because the extraction of these features needs to rely on network resources, but the network resources are scattered and not necessarily accurate, and its wrong information can easily lead to error cascades, so the disambiguation effect is not good

In the clustering algorithm stage, this stage is realized by improving the clustering algorithm or using multiple clustering methods, but this process needs to manually set the threshold or the number of categories, and it takes time to run when clustering algorithms are used for large-scale text data. Long, it is difficult to apply in the actual system; in addition, when adding text information, it is necessary to re-cluster all the text in the database, so it is not suitable for large-scale data processing

Images