Rapid customization of an information extraction system for a surprise language

Authors:
Diana Maynard;Valentin Tablan;Kalina Bontcheva;Hamish Cunningham
Affiliations:
University of Sheffield, UK;University of Sheffield, UK;University of Sheffield, UK;University of Sheffield, UK
Venue:
ACM Transactions on Asian Language Information Processing (TALIP)
Year:
2003

Citing 4
Cited 6

An Algorithm that Learns What‘s in a Name

Machine Learning - Special issue on natural language learning
A simple rule-based part of speech tagger

ANLC '92 Proceedings of the third conference on Applied natural language processing
A statistical profile of the Named Entity task

ANLC '97 Proceedings of the fifth conference on Applied natural language processing
Multilingual adaptations of ANNIE, a reusable information extraction tool

EACL '03 Proceedings of the tenth conference on European chapter of the Association for Computational Linguistics - Volume 2

NLP Techniques for Term Extraction and Ontology Population

Proceedings of the 2008 conference on Ontology Learning and Population: Bridging the Gap between Text and Knowledge
Modifying a natural language processing system for European languages to treat Arabic in information processing and information retrieval applications

Semitic '05 Proceedings of the ACL Workshop on Computational Approaches to Semitic Languages
A hybrid approach to align sentences and words in English-Hindi parallel corpora

ParaText '05 Proceedings of the ACL Workshop on Building and Using Parallel Texts
Aligning words in English-Hindi parallel corpora

ParaText '05 Proceedings of the ACL Workshop on Building and Using Parallel Texts
Natural language technology for information integration in business intelligence

BIS'07 Proceedings of the 10th international conference on Business information systems
Extreme extraction: machine reading in a week

EMNLP '11 Proceedings of the Conference on Empirical Methods in Natural Language Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes the rapid adaptation for surprise languages of a flexible and robust Information Extraction system based on GATE, a portable Natural Language Processing infrastructure. Our experiences show that even without a native speaker and in the absence of training data, we can quickly customize the system to a new language. We adapted the default English system for the Cebuano language in 10 days, achieving an F measure of 77.5%.