Three-order normalized PMI and other lessons in tensor analysis of verbal selectional preferences

Makrai Márton: Three-order normalized PMI and other lessons in tensor analysis of verbal selectional preferences. In: Magyar Számítógépes Nyelvészeti Konferencia, (18). pp. 105-120. (2022)

[thumbnail of msznykonf_018_105-120.pdf] Cikk, tanulmány, mű
msznykonf_018_105-120.pdf

Download (320kB)

Abstract

We investigate several questions in transitive verb structure representation by decomposing tensors populated with different subject-verb-object association measures, including a novel generalization of normalized pointwise mutual information to the higher-order (>2) case. Which association measure works the best in modeling verb structures? Should we include occurrences with unfilled arguments in our statistics? We also investigate qualitatively the latent dimensions, and the difference between each noun as a subject versus an object.

Item Type: Article
Heading title: Szintaxis
Journal or Publication Title: Magyar Számítógépes Nyelvészeti Konferencia
Date: 2022
Volume: 18
ISBN: 978-963-306-848-9
Page Range: pp. 105-120
Language: English
Place of Publication: Szeged
Event Title: Magyar számítógépes nyelvészeti konferencia (18.) (2022) (Szeged)
Related URLs: http://acta.bibl.u-szeged.hu/75797/
Uncontrolled Keywords: Nyelvészet - számítógép alkalmazása
Additional Information: Bibliogr.: p. 116-120. ; ill. ; összefoglalás angol nyelven
Subjects: 01. Natural sciences
01. Natural sciences > 01.02. Computer and information sciences
06. Humanities
06. Humanities > 06.02. Languages and Literature
Date Deposited: 2022. May. 24. 15:36
Last Modified: 2022. May. 24. 15:36
URI: http://acta.bibl.u-szeged.hu/id/eprint/75868

Actions (login required)

View Item View Item