Text Document Retrieval In English Using Keywords of Indonesian Dictionary Based

Abstract

Abstract— Cross language information regtrieval at the present moment is crucial to the amount of available information use the language variety. Mean while the user who have mastering another language is very less. So with the appointment system of cross language information retrieval is expected.Information retrieval applications on this system to search for text documents in English using keyword of Indonesian dictionary-based. This system was built by several stages starting from collection of documents data by using crawler, entering documents data into a corpus table, punctuation removal, tokenization of documents, stopword removal and term weighting.The ability of this system can add documents data, dictionaries data and stopword data. It is enable to retrieval text documents in English that contains keyword of Indonesian with dictionary-based. Results of documents retrieval was ranked based on the calculation of term weights. Able to see the contents of the document and open the original document. The development of this system can be used as a cross language information retrieval system on dictionary based.Keywords— retrieval information, dictionary based, cross language.