Offer

Expert Finder – semantic, recommendation system

Decision Support System which enables to find scientific expert matching keyword-query or document. Using relational data and semantic web, text-mining and NLP algorithm we designed and built recommendation system used to find reviewer’s candidates for a given document (i.e. abstract of project proposal, article), or to find expert in a domain who matches a given keywords. We built expert recommendation Systems which are deployed in the public agencies responsible for granting polish scientists.http://sssr.opi.org.pl/sssr-web/site/home?lang=en

Semantic searcher based on word sense discovery

Commonly used search engines retrieve results of a query as a flat list of most popular documents. Most of results are connected with dominating and most frequent senses of the query, what leads to lack of documents related to infrequent senses. Semanitc searcher provides results grouped in clusters concerning different senses of query. Rather than the results of a query being presented as a flat list, they are grouped on the basis of their similarity and subsequently shown to the user as a list of clusters. Each cluster is intended to represent a different meaning of the input query, thus taking into account the lexical ambiguity (i.e polysemy) issue. The prototype of this solution is used intenally in OPI in order to search through large textual data sets (containing: articles, project proposals, reviews, scientists profiles).