Method for extracting hyponymy relation of field terms from wikipedia

Abstract

The invention relates to a method for extracting a hyponymy relation of field terms from wikipedia. The method comprises the following steps of (1) using a wikipedia page corresponding to the field name as the starting page, carrying out the breadth-first traversal with the depth of 3, utilizing an URL (uniform resource locator) regular expression to filter the hyperlink not directing to the field term, and respectively storing the traversed page and hyperlink as the page text collection and the binary group collection; (2) obtaining the bidirectional link feature, edge betweenness feature and clustering coefficient feature from the binary group collection; obtaining the anchor text location feature and anchor text context feature from the text collection, and building five-dimensional feature vectors; (3) using a Random Forest classifier to carry out binary classifying on the hyperlink in the binary group collection according to the hyponymy relation and the non-hyponymy relation. The method has the advantage that the text feature and the hyperlink topology feature are comprehensively applied, so the hyponymy relation can be automatically extracted from the wiki.

Description

technical field [0001] The invention relates to an information extraction method, in particular to a method for extracting the hyponym relationship between field terms from Wikipedia. Background technique [0002] Hyponymy relation (Hyponymy relation) is the most basic semantic relationship between domain terms, which mainly describes the affiliation relationship between domain terms. For example, there is hyponymy between the two terms K-means algorithm and Cluster analysis in the field of "data mining". relation. The hyponymy relationship is the foundation of the classification system, and plays a fundamental role in the organization, management, classification, and retrieval of massive digital resources, especially digital resources related to the field (such as professional literature, textbooks, etc.). However, hyponymy relations are usually implicit in domain-related texts, and manual labeling of hyponymy relations is not only time-consuming and laborious, but also re...

AI Technical Summary

Problems solved by technology

Only based on a series of text features such as sentence structure features, term word frequency, part of speech, and part of speech, the accuracy of extraction is not high; secondly, word segmentation and part-of-speech tagging operations are involved in term extraction, and the results of these text preprocessing cannot be guaranteed to be completely correct. Limits the performance of subsequent hypernymy relationship extraction

Images