Method and device for mining hypernym-hyponym relation between domain-specific terms

Abstract

The invention provides a method and device for mining a hypernym-hyponym relation between domain-specific terms. The method includes: acquiring an entry explanation statement where first domain-specific terms are located, on a word bank page, according to a plurality of first preset domain-specific terms, wherein the first preset domain-specific terms are associates with first preset domain-specific term meaning; and acquiring a hypernym-hyponym relation between the first domain-specific terms and words included in the entry explanation statement by using a hypernym-hyponym relation model file which is generated in advance by a condition random field CRF tool. According to the scheme of the invention, the entry explanation statement where first domain-specific terms are located, on a word bank page is used, training and learning is performed by using a CRF robot learning technology, the model file is established finally, the hypernym-hyponym relation between the first domain-specific terms and the words included in the entry explanation statement is acquired by using the model file, and the accuracy of acquisition of the hypernym-hyponym relation can be improved.

Description

technical field [0001] The present invention relates to the technical field of data services, in particular to a method and device for mining the upper and lower relations between terms in the field. Background technique [0002] The hyponymy relationship is a kind of semantic relationship, which is often used in the construction and improvement of dictionaries, ontologies and knowledge bases. The hyponymy relationship in ontology learning refers to: Given two words D and U, for the meanings expressed by these two words, if U contains D, U and D are considered to have a hyponymy relationship, and U is the hypernymy of D concept, D is a sub-concept of U, denoted as ISA(D, U). For example, ISA (carbon dioxide, greenhouse gas), ISA (4G business travel package, tariff package). Apply the hypernymy relationship to the query expansion of search engines or automatic responses. For example, when a user searches for "4G business travel package", the superordinate concept of the sea...

AI Technical Summary

Problems solved by technology

[0007] First, the template-based method: due to the complexity of the Chinese language and the lack of semantic analysis in the pattern matching process, a large number of useless concept pairs will also be matched, which greatly reduces the accuracy of the extraction results; and due to the Chinese syntax Various forms, it is difficult to construct a relatively complete set of patterns

[0008] Secondly, the dictionary-based method: the cost of making, maintaining and updating the dictionary is too high, and it is difficult to find many professional domain terms in the general domain dictionary; when faced with applications in different fields, the explanation of specific terms is not sufficient. Must meet the requirements of the specific domain, which is the difficulty faced by dictionary-based methods

[0009] Therefore, based on the currently used methods for acquiring hyponymy relations, there are problems with relatively low accuracy and recall rates, that is, due to the inherent particularity and complexity of real language texts, the mining of hyponymy relations is very challenging.

Images