Detail publikace

Towards a Framework for Comparing Automatic Term Recognition Methods

Originální název

Towards a Framework for Comparing Automatic Term Recognition Methods

Anglický název

Towards a Framework for Comparing Automatic Term Recognition Methods

Jazyk

en

Originální abstrakt

Automatic Term Recognition focuses on the extraction of words and multi-word expressions that are significant for a given domain. There is a considerable interest in using ATR for automatic metadata generation, creation of thesauri and terminological glossaries, keyword extraction, ontology building, etc. This paper introduces a new ATR evaluation framework that consists of the open-source referential implementation of advanced ATR algorithms, annotated datasets and tools for the task-specific evaluation. We demonstrate the advantages of the framework on an experimental study comparing the base ATR methods as well as their combinations under various conditions. The created platform is freely available and prepared for extensions by other researchers.

Anglický abstrakt

Automatic Term Recognition focuses on the extraction of words and multi-word expressions that are significant for a given domain. There is a considerable interest in using ATR for automatic metadata generation, creation of thesauri and terminological glossaries, keyword extraction, ontology building, etc. This paper introduces a new ATR evaluation framework that consists of the open-source referential implementation of advanced ATR algorithms, annotated datasets and tools for the task-specific evaluation. We demonstrate the advantages of the framework on an experimental study comparing the base ATR methods as well as their combinations under various conditions. The created platform is freely available and prepared for extensions by other researchers.

BibTex


@inproceedings{BUT33745,
  author="Petr {Knoth} and Marek {Schmidt} and Pavel {Smrž} and Zdeněk {Zdráhal}",
  title="Towards a Framework for Comparing Automatic Term Recognition Methods",
  annote="Automatic Term Recognition focuses on the extraction of words and multi-word
expressions that are significant for a given domain. There is a considerable
interest in using ATR for automatic metadata generation, creation of thesauri and
terminological glossaries, keyword extraction, ontology building, etc. This paper
introduces a new ATR evaluation framework that consists of the open-source
referential implementation of advanced ATR algorithms, annotated datasets and
tools for the task-specific evaluation. We demonstrate the advantages of the
framework on an experimental study comparing the base ATR methods as well as
their combinations under various conditions. The created platform is freely
available and prepared for extensions by other researchers.",
  address="Faculty of Informatics and Information Technology Slovak University of Technology in Bratislava",
  booktitle="Znalosti 2009",
  chapter="33745",
  edition="8th Annual Conference, Brno",
  howpublished="print",
  institution="Faculty of Informatics and Information Technology Slovak University of Technology in Bratislava",
  year="2009",
  month="february",
  pages="83--94",
  publisher="Faculty of Informatics and Information Technology Slovak University of Technology in Bratislava",
  type="conference paper"
}