Constructing a Lexicon of Dutch Discourse Connectives

Authors

  • Peter Bourgonje Universit¨at Potsdam, Germany
  • Jet Hoek Universiteit Utrecht, The Netherlands
  • Jacqueline Evers-Vermeul Universiteit Utrecht, The Netherlands
  • Gisela Redeker Rijksuniversiteit Groningen, The Netherlands
  • Ted Sanders Universiteit Utrecht, The Netherlands
  • Manfred Stede Universit¨at Potsdam, Germany

Abstract

We present a lexicon of Dutch Discourse Connectives (DisCoDict). Its content was obtained using a two-step process, in which we first exploited a parallel corpus and a German seed lexicon, and then manually evaluated the candidate entries against existing connective resources for Dutch, using these resources to complete our lexicon. We compared connective definitions in the research traditions of the two languages and accommodated the differences in our final lexicon. The DisCoDict lexicon is made publicly available, both human- and machine-readable, and targeted at practical use cases in the domain of automatic discourse parsing. It also supports manual investigations of discourse structure and its lexical signals.

Downloads

Published

2018-12-01

How to Cite

Bourgonje, P., Hoek, J., Evers-Vermeul, J., Redeker, G., Sanders, T., & Stede, M. (2018). Constructing a Lexicon of Dutch Discourse Connectives. Computational Linguistics in the Netherlands Journal, 8, 163–175. Retrieved from https://www.clinjournal.org/clinj/article/view/85

Issue

Section

Articles

Most read articles by the same author(s)