Ricerc@Sapienza

In this paper, we present WebIsAGraph, a very large hypernymy graph compiled from a dataset of is-a relationships extracted from the CommonCrawl. We provide the resource together with a Neo4j plugin to enable efficient searching and querying over such large graph. We use WebIsAGraph to study the problem of detecting polysemous terms in a noisy terminological knowledge graph, thus quantifying the degree of polysemy of terms found in is-a extractions from Web text.

In this demo paper, we present ARCA, a visual-search based system that allows the semantic exploration of a bookstore. Navigating a domain-specific knowledge graph, students and researchers alike can start from any specific concept and reach any other related concept, discovering associated books and information. To achieve this paradigm of interaction we built a prototype system, flexible and adaptable to multiple contexts of use, that extracts semantic information from the contents of a books' corpus, building a dedicated knowledge graph that is linked to external knowledge bases.