| Abstract [eng] |
Summarizer is useful system, which allows compressing text and represents it in a shorter way. In Lithuania summarizers are new technology and information about them is poor, although these systems are created and developed by computational linguistics specialists in other countries. In summarizers’ research English and Lithuanian texts were used, which allowed seeing differences between received summaries. In the English texts, summaries using all summarizers were quite informative, useful and did not loose main information from original texts, except cases when a high compression rate was used. While using for summarization Lithuanian texts, some summarizers confront with language recognition problem – summaries in Lithuanian are with unrecognizable symbols, or in individual cases these symbols are missing. Summaries in Lithuanian language are not of the same quality as summaries in English. It was also noticed, that Lithuanian summaries with higher compression rate are loosing original text meaning, information and their usefulness. Analyzed summarizers are best fitted for English language, therefore using summarizer for other language than English stipulates various problems – from language recognition to rendering of text meaning. It is very important to adapt different languages to summarizers, as this would significantly improve summarizers. Thats why were tries to make a summarizer to Lithuanian language texts. Results of summarizer creation lets to make conlusion, that summarizers designed to Lithuania language should use more than one method of summarization, and sentence length method not allways can be effective. Findings of this paper can be used in creating Lithuanian summarizer or improving other summarizers. |
