• Aucun résultat trouvé

Semantic Search: from Names and Phrases to Entities and Relations

N/A
N/A
Protected

Academic year: 2022

Partager "Semantic Search: from Names and Phrases to Entities and Relations"

Copied!
1
0
0

Texte intégral

(1)

Semantic Search: from Names and Phrases to Entities and Relations

– Invited speech –

Gerhard Weikum

Max-Planck-Institut f ¨ur Informatik

Department of Databases and Information Systems 66123 Saarbr ¨ucken, Germany

weikum@mpi-inf.mpg.de

ABSTRACT

Web search is traditionally limited to keyword queries. In the era of Big Data and the Web of Linked Data, one would expect that schema-free search over both text and structured key-value pairs becomes more semantic, Systems should, for example, identify entities in queries and return crisp answers referring to facts, other entities and relationships.

Some of these desired advances are happening now; the Google Knowledge Graph, Microsoft Entity Cube, and IBM’s Watson tech- nology for question answering are examples. However, all these systems still have major limitations when dealing with ambiguous names and phrases that need to be mapped to entities and relations in the underlying data and knowledge bases.

This talk discusses recent and ongoing research on disambiguat- ing names and phrases. The presented methods can boost the quality and extent of semantic search, machine reading, knowledge harvest- ing, and question answering over Web contents.

Speaker Short Bio

Gerhard Weikum is a Research Director at the Max-Planck Institute for Informatics (MPII) in Saarbruecken, Germany, where he is leading the department on databases and information systems.

He is also an adjunct professor in the Department of Computer Science of Saarland University in Saarbruecken, Germany, and he is a principal investigator of the Cluster of Excellence on Multimodal Computing and Interaction.

Earlier he held positions at Saarland University in Saarbruecken, Germany, at ETH Zurich, Switzerland, at MCC in Austin, Texas, and he was a visiting senior researcher at Microsoft Research in Red- mond, Washington. He received his diploma and doctoral degrees from the University of Darmstadt, Germany.

VLDS’12 August 31, 2012. Istanbul, Turkey.

Copyrightc 2012 for the individual papers by the papers’ authors. Copying permitted for private and academic purposes. This volume is published and copyrighted by its editors.

Références

Documents relatifs

Our approach for effective search over the structured, social and semantic graph re- lies on two core ingredients: (i) a model of relationships between keywords and various

A system for creating and naming machine-interpretable descriptions of groups of organisms, the Semantic Vernacular System, is proposed as a solu- tion for creating such

Structured information is best represented in a knowledge base (the semantics is then explicit in the data) but the bulk of our knowledge of the world will always be in the form

Using input from [3], the current work focuses on integration and searching multiple open drug Linked Data sources for general information needs proposed by at least 25% of

In this article we will describe two different vocabularies/models for rep- resenting lexico-semantic data on the Semantic Web: in the first case from a synchronic perspective, that

The design of URIs satisfies the Linked Data principles 1) and 2). We also provide relevant information for the URI of each entity, and this implementation helps satisfy the

In this paper, we present a novel approach that leverages the small graph patterns oc- curring in the Linked Open Data (LOD) to automatically infer the se- mantic relations within

In order to avoid the need for users to specify a complex structured query upfront [2, 4] or for local free-text indexes to be built [5, 6], we propose an approach that combines