header

Contextualized Ranking of Entity Types Based on Knowledge Graphs

37 Pages Posted: 24 Jun 2018 First Look: Accepted

See all articles by Alberto Tonon

Alberto Tonon

University of Fribourg - Xascale Infolab

Michele Catasta

ETH Zürich

Roman Prokofyev

University of Fribourg - Xascale Infolab

Gianluca Demartini

L3S Research Center

Karl Aberer

ETH Zürich

Philippe Cudre-Mauroux

University of Fribourg - Xascale Infolab

Abstract

A large fraction of online queries targets entities. For this reason, Search Engine Result Pages (SERPs) increasingly contain information about the searched entities such as pictures, short summaries, related entities, and factual information. A key facet that is often displayed on the SERPs and that is instrumental for many applications is the entity type. However, an entity is usually not associated to a single generic type in the background knowledge graph but rather to a set of more specific types, which may be relevant or not given the document context. For example, one can find on the Linked Open Data cloud the fact that Tom Hanks is a person, an actor, and a person from Concord, California. All these types are correct but some may be too general to be interesting (e.g., person), while other may be interesting but already known to the user (e.g., actor), or may be irrelevant given the current browsing context (e.g., person from Concord, California). In this paper, we define the new task of ranking entity types given an entity and its context. We propose and evaluate new methods to find the most relevant entity type based on collection statistics and on the knowledge graph structure interconnecting entities and types. An extensive experimental evaluation over several document collections at different levels of granularity (e.g., sentences, paragraphs) and different type hierarchies (including DBpedia, Freebase, and schema.org) shows that hierarchy-based approaches provide more accurate results when picking entity types to be displayed to the end-user.

Keywords: Entity Typing, Ranking, Context, Crowdsourcing, Knowledge Graphs

Suggested Citation

Tonon, Alberto and Catasta, Michele and Prokofyev, Roman and Demartini, Gianluca and Aberer, Karl and Cudre-Mauroux, Philippe, Contextualized Ranking of Entity Types Based on Knowledge Graphs (2016). Journal of Web Semantics First Look 37_0_10. Available at SSRN: https://ssrn.com/abstract=3199222 or http://dx.doi.org/10.2139/ssrn.3199222

Alberto Tonon (Contact Author)

University of Fribourg - Xascale Infolab ( email )

Bd de Pérolles 90
Fribourg
Switzerland

Michele Catasta

ETH Zürich ( email )

Lausanne
Switzerland

Roman Prokofyev

University of Fribourg - Xascale Infolab

Bd de Pérolles 90
Fribourg
Switzerland

Gianluca Demartini

L3S Research Center ( email )

Appelstrasse 9a
Hannover, D-30167
Germany

Karl Aberer

ETH Zürich ( email )

Lausanne
Switzerland

Philippe Cudre-Mauroux

University of Fribourg - Xascale Infolab ( email )

Bd de Pérolles 90
Fribourg
Switzerland

Register to save articles to
your library

Register

Paper statistics

Abstract Views
133
Downloads
7