Semantics and Usage Statistics for Multi-Dimensional Query Expansion

However, unlike the positional relevance model [12] which is a formal approach for QE ex- tending the relevance Language Model (LM) [10], we believe that the suitability of

Various kinds of denotational semantics have helped in reasoning about the properties of entire type systems and also of specific typed terms. E-variables pose serious challenges

This paper overcomes these difficulties and gives a complete semantics for an intersection type system with an arbitrary (possibly infinite) number of expansion variables using

According to the Table 1, we can see that the system obtain optimal results when using the two query expansion techniques, along with 5 heuristics features, namely

We presented our approach for query expansion, which includes concept can- didates generation from Wikipedia and DBpedia, and the selection of K-best concepts according to the

In the course of these previous experiments, we had made a certain number of observations related to the difficulties encountered in patent data, the challenges

Query expansion in the bilingual tasks (denoted by “X” at the end of the names in Table 3) added the source topics from the translation and an additional translation of the topics

Fi- nally, to improve the accuracy of SPARQL query generated, we evaluate the semantic importance of each word in a question via TF-IDF dur- ing the generating queries