A subject-class-based cross-lingual biomedical research paper information recommendation method

Abstract

The present invention relates to the technical field of information retrieval and recommendation systems, and more particularly, to a subject-class-based cross-lingual biomedical research paper information recommendation method. The method mainly comprises the following steps of: carrying out data preprocessing on the text data, applying the PLAS model to text clustering, calculating the word vector information of each subject grouping, obtaining the most relevant cross-language subject number of each subject, reading the retrieval word group input by the user, judging the retrieval word groupof the user, obtaining the recommendation result of the Chinese article and the recommendation of the English literature and so on. The invention realizes the dimensionality reduction of the analysisof the text from the word frequency space to the spatial subject space. The method of data dimension reduction can effectively reduce the dependence of the model on translation methods, which is conducive to cross-linguistic literature feature analysis. At the same time, topic model can effectively mine the semantic information in documents, discover the potential association between documents, and effectively solve the problem of polysemy and monosyllabic multi-word.

Description

technical field [0001] The present invention relates to the technical fields of information retrieval and recommendation systems, and more specifically, to a topic-based method for recommending information on cross-language biomedical academic papers. Background technique [0002] In the text recommendation system, the most commonly used method is to use the Term Frequency-Invert Document Frequency (TF-IDF) method to convert the document into a vector representation of the term frequency dimension. Then, the similarity between documents is calculated by the distance of word vectors, so as to make content-based recommendations. As a statistical method, TF-IDF only considers the word frequency information of words appearing in documents, but cannot mine semantic information and statistical information within and between documents. This information is often the best feature that reflects the content of the document. For document processing in different languages, TF-IDF canno...

AI Technical Summary

Problems solved by technology

These phenomena often occur in the processing of document information, which will directly affect the recommendation results and make them deviate from the real needs of users.

In dealing with cross-language retrieval problems, many scholars have also tried to use various methods to optimize the effect of machine translation, but they still cannot do without the dependence on translation dictionaries or bilingual control corpora. The professionalism and particularity of academic literature makes the translation model The difficulty of modeling increases, and the effect of the model is low

Images