Fasilkom Ul at TREC 2011 entity list completion task

Ananda Budi Prasetya, Hapnes Toba, Mirna Adriani, Hisar Maruli Manurung

Research output: Contribution to journalConference articlepeer-review

Abstract

In this paper we describe our submissions to the TREC 2011 Entity Track. We have experimented with several combined approaches to search the entity candidates, i.e.: by resolving the linguistic relation of the given entity, query expansion by example to broader the retrieval results, and ontology approach to identify the named entity from the search result snippets and to retrieved the candidate entity. We rank the entity candidates based onthe frequency of each entity in the web search result snippets. At the end of our system architecture we performed phrase-based search mechanism in the Sindice dump collection to retrieve specific URIs final entity list.

Original languageEnglish
JournalNIST Special Publication
Publication statusPublished - 1 Dec 2011
Event20th Text REtrieval Conference, TREC 2011 - Gaithersburg, MD, United States
Duration: 15 Nov 201118 Nov 2011

Fingerprint Dive into the research topics of 'Fasilkom Ul at TREC 2011 entity list completion task'. Together they form a unique fingerprint.

Cite this