توجه: محتویات این صفحه به صورت خودکار پردازش شده و مقاله‌های نویسندگانی با تشابه اسمی، همگی در بخش یکسان نمایش داده می‌شوند.
۱Using Support Vector Machines Classifier fo Improve the Performance of Reinforcement Learning based Web Crawlers
اطلاعات انتشار: نهمین کنفرانس سالانه انجمن کامپیوتر ایران، سال
تعداد صفحات: ۸
The main contribution of this paper is introducing an approach for expanding the crawling methods of Cora spider, as a RL–based spider. We have introduced novel methods for calculating the Q–Value in reinforcement learning module of the spider. The proposed crawlers can find the target pages faster and earn more rewards over the crawl than Cora’s crawlers. We have used support Vector Machines (SVMs) classifier for the first time as a text learner in Web crawlers and compared the results with crawlers which use Naïve Bayes (NB) classifier for this purpose. The results show that crawlers using SVMs outperform crawlers which use NB in the first half of crawling a web site and find the target pages more quickly. The test bed for the evaluation of our approaches was Web sites of four computer science departments of four universities, which have been made available offline.<\div>

۲A New Approach to Expand User's Query in Domain Specific Search Engines
اطلاعات انتشار: هشتمین کنفرانس سالانه انجمن کامپیوتر ایران، سال
تعداد صفحات: ۸
Most of popular search engines accept user's query as a set of keywords. But, keywords are not powerful enough for comprehensive representation of user request. In this paper, we introduce “Domain Specific Concept Hierarchy (DSCH)” as a specialization of concept hierarchies. Then we propose a new algorithm for automatic construction of DSCH. Using this hierarchy in a domain specific search engine, search engine expands the user's query by adding a set of conceptually related terms to query. The proposed algorithm has been implemented
and the results are presented. We have used DSCH in AKU–CS domain specific search engine. The result shows significant improvement in quality of results of search engine so that it returns results that are more relevant to the user’s query with higher ranks in comparison with
original search engine, which does not use query expansion. We used Cora search engine that is a computer science papers search engine as original system.<\div>
نمایش نتایج ۱ تا ۲ از میان ۲ نتیجه