Search

Ranking algorithms, as the core of web search systems, are responsible for finding and ranking the most relevant documents to user information needs from the crawled and indexed corpus. With the ever-increasing amount of available training data, ranking technologies are moving towards using Machine Learning methods, described as Learning to Rank algorithms. The basic Learning to Rank systems mainly have used textual features while ignoring semantic features. With the advent of Semantic Web, there is an emerging interest in developing and using semantic features for Learning to Rank systems. An important challenge is that there is currently no comprehensive study on the combined usage of textual and semantic features for Learning to Rank systems. In this paper, first, we define and implement four new sets of semantic features based on Knowledge Graph, Entity Repetition, Textual Fields and Vector Representation of Words and Texts. For experimental analysis, we used the MQ-2007 dataset from LETOR 4, which includes a set of textual features. The results of running six standard Learning to Rank Algorithms show that by using semantic features, either in isolation or in combination with textual features, significantly increases the performance. The increase in performance is even more significant when we limit the tests to hard queries. We also implemented an existing Feature Selection algorithm to test whether it can improve the results even further. The results showed improvements for some Learning to Rank algorithms, yet failed to improve on others. [ABSTRACT FROM AUTHOR]

The aim of ontology matching is to find similarities or matches between concepts of different ontologies. There are many new applications which need a sort of ontology matching. Some examples comprises of semantic web applications, multi agent systems, applications mash up and so on. One may be interested in either finding lexical similarity or semantic similarity, but in the both cases, the result of such a matching process can be useful for relating distinct ontologies. Leveraging ontology matching system enables us to reuse existing ontologies in new applications and save costs by eliminating the need for developing new ontologies. Among current algorithms proposed for matching onologies applying machine learning techniques is a promising one. However, there are some problems regarding the results of these methods which are mainly due to poor features used in learning process. In this paper we propose a new method in which a text corpus is used as the source of knowledge in conjunction with a machine learning method to find matching between two ontologies .The main objective in this new method is to find similarity of two concepts based on similarity of their instances. We show how contextual knowledge hidden in domain specific documents can help us to boost the machine learning methods by providing enough features. Also we show how taking benefit from this knowledge transcends the current approaches merely detect lexical similarity by either recognizing semantic similarity of concepts. [ABSTRACT FROM AUTHOR]