A hybrid approach to NER by integrating manual rules into MEMM

Moshe Fresko, Binyamin Rozenfeld, Ronen Feldman

Research output: Contribution to conferencePaperpeer-review

1 Scopus citations

Abstract

This paper describes a framework for defining domain specific Feature Functions in a user friendly form to be used in a Maximum Entropy Markov Model (MEMM) for the Named Entity Recognition (NER) task. Our system called MERGE allows defining general Feature Function Templates, as well as Linguistic Rules incorporated into the classifier. The simple way of translating these rules into specific feature functions are shown. We show that MERGE can perform better from both purely machine learning based systems and purely-knowledge based approaches by some small expert interaction of rule-tuning.

Original languageEnglish
StatePublished - 2006
Event9th International Symposium on Artificial Intelligence and Mathematics, ISAIM 2006 - Fort Lauderdale, FL, United States
Duration: 4 Jan 20066 Jan 2006

Conference

Conference9th International Symposium on Artificial Intelligence and Mathematics, ISAIM 2006
Country/TerritoryUnited States
CityFort Lauderdale, FL
Period4/01/066/01/06

Keywords

  • Information extraction
  • Machine learning
  • Named entity recognition

Fingerprint

Dive into the research topics of 'A hybrid approach to NER by integrating manual rules into MEMM'. Together they form a unique fingerprint.

Cite this