A name ambiguity eliminating method applied to Web figure search

Abstract

The invention discloses a name ambiguity eliminating method applied to Web task searching, which comprises the following steps of S1, extracting an HTML webpage source code, and extracting noise irrelevant to character information from the HTML webpage source code; S2, extracting a character webpage feature set; S3, generating a combined feature vector representing a certain person related webpagefrom the person webpage feature set extracted in the step S2; S4, performing hierarchical clustering by adopting a condensation hierarchical clustering algorithm to obtain a character webpage clustering result. According to the method, through introduction of the n-element capital model, the limitation of traditional named entity recognition is solved, named entity extraction is limited, and a plurality of special vocabularies and special vocabularies in the text cannot be extracted; different extracted features are endowed with different weights according to the importance of the features tothe character representation, so that the name disambiguation accuracy is improved.

Description

technical field [0001] The invention belongs to the field of photoelectric transmission, in particular to an all-fiber distributed acoustic wave sensing technology. Background technique [0002] With the advent of the mobile Internet era, search engines have become an important tool for people to acquire knowledge, and it is very common to search for personal information on the Internet. According to statistics, about 5%-10% of search engine queries involve names, and only less than 20% of people are willing to add additional information when searching for names. At the same time, personal names are highly ambiguous. According to the report of the US Census Bureau, there are 1 billion people who use only 90,000 different names. The name retrieval of the search engine gets mixed results of multiple related webpages with the same name, and there is a tendency for "celebrity" webpages to overwhelm "non-celebrity". For example, if Google searches for "Michael Jordan", the resu...

AI Technical Summary

Problems solved by technology

[0013] Existing Web name disambiguation technologies have some shortcomings, such as the classification method based on network knowledge resources requires that people with the same name cannot have the same occupation, and the clustering method based on graph segmentation requires that the social circles between people with the same name do not overlap much, etc.

In addition, for the clustering method based on the vector space model, the previous feature selection and processing reasons, as well as the reasons for the feature set fusion method, lead to certain limitations in using the clustering method based on the vector space model for Web name disambiguation

Images