Synonym Discovery Based On The Searching Information

With the rapid development of computer technology,the application of searching engine has gone deep into daily life.With the searching of the information has became more and more frequent,accuratly searching become more and more challenging.How to more accurately understanding the keywords that the users want to search from the vast information resource database,making the keyword searching content more expanding and more accuratly recommending,is an important topic in the field of information retrieval.The traditional information retrieval service has gradually failed to meeting the user's searching requirements,so,an intelligent,concept-based information retrieval system has became a future direction of development.Identifying alternative synonyms for user searching keywords is one of the most important ways to achieve intelligent information retrieval.To achieving efficiently synonym expansion,we need a powerful synonym dictionary.Synonyms defined in this article are words that can be substituted for each other in similar contexts.With the changes of the time,the application of language is changing with each passing day,and the use of the traditional thesaurus to judging or finding synonyms is completely inapplicable.it is imperative to find new synonym tables.In recent years,with the progress of natural language processing technology,there are more and more studies on synonym,and fields of synonym that need to be used.,the researchers put forward many advanced matching synonym discrimination and synonym set extraction method based on corpus.In this paper,using searching information to discoverying synonym,it is different from the synonym discovery based on specific business searching information.By designing alignment rules and phrase pair extraction rules,finding the synonyms discovery method without specific business data;applies the distributed representation word vector to feature engineering;determining the synonym pairs by training the machine learning model,and using the model to determining the synonyms.synonyms are extracted from the database.In this paper,using this kind of data to discovery the synonym table,combining statistical characteristics and distributed depresentation word vector to retrieve information,overcomes the disadvantages of the traditional synonym table,which can't find new words and unregistered words.The automatic discovery and identification of synonym has great significance in the field of concept-based information retrieval.Based on the research and analysis of the similarity algorithm and synonym recognition algorithm,this paper makes an in-depth study on the synonym discovery method base on the searching information.