Method and device for calculating text similarity and searching processing realized by computer

Abstract

The invention provides a method and a device for calculating text similarity and realizing search processing achieved through a computer. The method comprises the following steps: acquiring a first text cluster and a second cluster; decoding the first text cluster according to a preset phrase translation model and a dependency structure model to obtain K translation text clusters; respectively calculating a first semantic similarity value between the K translation text clusters and the second text cluster, and calculating a second semantic similarity value between the first text cluster and the second text cluster according to the K calculated semantic similarity values. By adopting the method and the device, the problem of long distance dependency relationship in sentences is solved, the semantics of searched sentences can be relatively well expressed, the searched sentences can be relatively well matched with webpage titles, and a user can obtain semantic matching search result items, so that the search experience of the user is improved.

Description

technical field [0001] The invention relates to natural language processing technology, in particular to a computer-implemented method and device for calculating text similarity and searching. Background technique [0002] Among search engines, in order to be able to match the search term (or Query) input by the user to each domain of the document (for example, title, content) as well as possible, a method based on complete word matching is usually used to realize the match. [0003] At present, there are also methods that use translation models. From the perspective of translation, it is assumed that titles and search terms (for example, Query) are written in different sub-languages, to translate similar "effective" into "useful". Phrase translation to achieve semantic matching. However, this method cannot solve the problem of long-distance dependence in the target language. It can only perform semantic matching simply, so that the semantics of the search statement cannot...

AI Technical Summary

Problems solved by technology

However, this method cannot solve the problem of long-distance dependence in the target language. It can only perform semantic matching simply, so that the semantics of the search statement cannot be truly reflected and expressed, so that the search statement and the title of the web page are incorrectly matched, which affects the display of search results. and sorting, which in turn affects the user experience

For example, match the sentence "Why didn't Guan Yu kill Cao Cao back then" to "Why didn't Cao Cao kill Guan Yu back then", in the original sentence (query), "Guan Yu" is the subject, "Cao Cao" is the object, and because the problem of long-distance dependency is not solved , the search statement and the title of the webpage only match words, but the dependency relationship of the actual sentence is not reflected

Images