License
When quoting this document, please refer to the following
URN: urn:nbn:de:0030-drops-3354
URL: http://drops.dagstuhl.de/opus/volltexte/2005/335/
Go to the corresponding Portal

Boguraev, Branimir ; Ando, Rie Kubota

TimeBank-Driven TimeML Analysis

pdf-format:
Document 1.pdf (432 KB)

Abstract

The design of TimeML as an expressive language for temporal information brings promises, and challenges; in particular, its representational properties raise the bar for traditional information extraction methods applied to the task of text-to-TimeML analysis. A reference corpus, such as TimeBank, is an invaluable asset in this situation; however, certain characteristics of TimeBank---size and consistency, primarily---present challenges of their own. We discuss the design, implementation, and performance of an automatic TimeML-compliant annotator, trained on TimeBank, and deploying a hybrid analytical strategy of mixing aggressive finite-state processing over linguistic annotations with a state-of-the-art machine learning technique capable of leveraging large amounts of unannotated data. The results we report are encouraging in the light of a close analysis of TimeBank; at the same time they are indicative of the need for more infrastructure work, especially in the direction of creating a larger and more robust reference corpus.

BibTeX - Entry

@InProceedings{boguraev_et_al:DSP:2005:335,
  author =	{Branimir Boguraev and Rie Kubota Ando},
  title =	{TimeBank-Driven TimeML Analysis},
  booktitle =	{Annotating, Extracting and Reasoning about Time and Events},
  year =	{2005},
  editor =	{Graham Katz and James Pustejovsky and Frank Schilder},
  number =	{05151},
  series =	{Dagstuhl Seminar Proceedings},
  ISSN =	{1862-4405},
  publisher =	{Internationales Begegnungs- und Forschungszentrum f{\"u}r Informatik (IBFI), Schloss Dagstuhl, Germany},
  address =	{Dagstuhl, Germany},
  URL =		{http://drops.dagstuhl.de/opus/volltexte/2005/335},
  annote =	{Keywords: TimeML analysis, TimeBank corpus, TimeML-compliant temporal information extraction, finite-state processing, machine learning, corpus analysis}
}

Keywords: TimeML analysis, TimeBank corpus, TimeML-compliant temporal information extraction, finite-state processing, machine learning, corpus analysis
Seminar: 05151 - Annotating, Extracting and Reasoning about Time and Events
Issue Date: 2005
Date of publication: 15.11.2005

DROPS-Home | Fulltext Search | Imprint Published by LZI