Named Entity Extraction and Linking Challenge: University of Twente at #Microposts2014

Mena Badieh Habib, Maurice van Keulen, Zhemin Zhu

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

1 Citation (Scopus)
10 Downloads (Pure)


Twitter is a potentially rich source of continuously and instantly updated information. Shortness and informality of tweets are challenges for Natural Language Processing (NLP) tasks. In this paper, we present a hybrid approach for Named Entity Extraction (NEE)and Linking (NEL) for tweets. Although NEE and NEL are two topics that are well studied in literature, almost all approaches treated the two problems separately. We believe that disambiguation (linking) could help improving the extraction process. We call this potential for mutual improvement, the reinforcement effect. It mimics the way humans understand natural language. Furthermore, our proposed approaches handles uncertainties involved in the two processes by considering possible alternatives.
Original languageEnglish
Title of host publicationProceedings of the the 4th Workshop on Making Sense of Microposts (#Microposts2014)
Subtitle of host publication Big things come in small packages: at the 23rd International World Wide Web Conference (WWW 2014)
EditorsMatthew Rowe, Milan Stankovic, Aba-Sah Dadzie
Place of PublicationAachen
Number of pages2
Publication statusPublished - Apr 2014
Event4th Workshop on Making Sense of Microposts (#Microposts2014): Big things come in small packages - Seoul, Korea, Republic of
Duration: 7 Apr 20147 Apr 2014
Conference number: 4

Publication series

NameCEUR Workshop Proceedings
ISSN (Print)1613-0073


Workshop4th Workshop on Making Sense of Microposts (#Microposts2014)
CountryKorea, Republic of


  • EWI-24669
  • Named entity extractionNamed entity disambiguationNamed entity recognitionNamed entity linkingTwitterTweetsMicroblogs
  • Social Media Analysis
  • IR-90689
  • Named Entity Linking
  • Twitter Messages
  • METIS-304067
  • Named Entity Extraction

Fingerprint Dive into the research topics of 'Named Entity Extraction and Linking Challenge: University of Twente at #Microposts2014'. Together they form a unique fingerprint.

Cite this