ATTENTION/WARNING - NE PAS DÉPOSER ICI/DO NOT SUBMIT HERE

Ceci est la version de TEST de DIAL.mem. Veuillez ne pas soumettre votre mémoire sur ce site mais bien à l'URL suivante: 'https://thesis.dial.uclouvain.be'.
This is the TEST version of DIAL.mem. Please use the following URL to submit your master thesis: 'https://thesis.dial.uclouvain.be'.
 

Designing and evaluating the Phraseology Extraction Package with a focus on nested n-grams and variation

Castiaux, Laurane
(2021)

Files

Castiaux_25771600_2021.pdf
  • Open access
  • Adobe PDF
  • 819.75 KB
Download

Details

Supervisors
Paquot, Magali
Faculty
Faculté de philosophie, arts et lettres
Degree label
Master [120] en linguistique, à finalité spécialisée: traitement automatique du langage
Abstract
This thesis aims at describing and evaluating the Phraseology Extraction Package (PEP), a command-line tool that was designed for automatic multi-word unit (MWU) extraction. This highly customisable tool has made two main contributions to the study of phraseology: 1) it offers a good handling of nested n-grams and 2) it integrates more variation and flexibility in the MWUs by including, not only tokens, but also lemmas and part of speech tags. By revisiting a study on different varieties of English with PEP instead of WordSmith tools, it was demonstrated that different results are obtained when nested n-grams and variation are taken into account instead of 3-grams. Thanks to its many customisable settings and its two different output formats (text and csv), it was illustrated how PEP can help conduct both a quantitative and qualitative analysis on MWUs.

Citations

  • APA

Castiaux, L. (2021). Designing and evaluating the Phraseology Extraction Package with a focus on nested n-grams and variation. https://dial-mem.test.bib.ucl.ac.be/handle/2078.2/25225