Applying a Word-sense Induction System to the Automatic Extraction of Diverse Dictionary Examples

By November 17, 2016,
Page 319-328
Author Paul Cook, Michael Rundell, Jey Han Lau, and Timothy Baldwin
Title Applying a Word-sense Induction System to the Automatic Extraction of Diverse Dictionary Examples
Abstract There have been many recent efforts to automate or semi-automate parts of the process of compiling a dictionary, including building headword lists and identifying collocations. The result of these efforts has been both to make lexicographers’ work more efficient, and to improve dictionaries by introducing more systematicity into the process of their construction. One task that has already been semi-automated is that of finding good dictionary examples, and a system for this, GDEX, is readily available in the Sketch Engine. An ideal system, however, would be able to automatically retrieve candidate examples of a particular sense of a word, which is beyond the current scope of GDEX. In this paper, as a step towards this ambitious goal, we propose and evaluate a method for applying a ‘word-sense induction’ system to automatically extract examples that exhibit a greater diversity of usages of a target word than can currently be obtained through GDEX. We then discuss the future prospects for systems that are able to automatically select candidate dictionary examples for a particular word sense.
Session Lexicography and Language Technologies
Keywords dictionary examples; word-sense induction; computational lexicography
BibTex
@InProceedings{ELX2014-022,
author={Paul Cook and Michael Rundell and Jey Han Lau and and Timothy Baldwin},
title={Applying a Word-sense Induction System to the Automatic Extraction of Diverse Dictionary Examples},
pages={319-328},
booktitle={Proceedings of the 16th EURALEX International Congress},
year={2014},
month={jul},
date={15-19},
address={Bolzano, Italy},
editor={Abel, Andrea and Vettori, Chiara and Ralli, Natascia},
publisher={EURAC research},
isbn={978-88-88906-97-3},
}
Download