Data Science

Wednesday, September 12, 2018 - 10:30 to 12:00
Danube Suite 3


Lexical and Statistical Semantics in Professional Search

How serious can a missing document on a search result list be? For certain people that conduct search as part of their profession, a missing search result could lead to litigation or death. This talk will examine search tasks in two such professional domains: Intellectual Property and Medicine, covering the challenges inherent in search in these domains. On the technical side, the analysis of documents using both lexical semantics and statistical semantics in order to improve search results in these domains will be presented.

Wikidata: The Linked Open Data hub

Wikipedia has long been the place to look up information about all sorts of subjects. In 2012 Wikimedia (the organization behind Wikipedia) started Wikidata: a central storage for the structured data of its Wikimedia sister projects including Wikipedia, Wikivoyage, Wikisource, and others.

WIkidata contains structured data about all subjects covered in Wikipedia and much more. It's freely usable and all the data can be downloaded or queried using SPARQL.

SemSur: A Core Ontology for the Semantic Representation of Research Findings

The way how research is communicated using text publications has not changed much over the past decades. We have the vision that ultimately researchers will work on a common structured knowledge base comprising comprehens- ive semantic and machine-comprehensible descriptions of their research, thus making research contributions more transparent and comparable. We present the SemSur ontology for semantically capturing the information commonly found in survey and review articles.