Discovering and Applying Geometric Properties for Probing Contextualized Representations

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3ANF2LIKLW" target="_blank" >RIV/00216208:11320/23:NF2LIKLW - isvavai.cz</a>

Result on the web

<a href="https://search.proquest.com/openview/ced2fcec12189e5c8e9839fce3bdbc3c/1?pq-origsite=gscholar&cbl=18750&diss=y" target="_blank" >https://search.proquest.com/openview/ced2fcec12189e5c8e9839fce3bdbc3c/1?pq-origsite=gscholar&cbl=18750&diss=y</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Discovering and Applying Geometric Properties for Probing Contextualized Representations

Original language description

"This dissertation studies the use of geometric properties to justify the impressive performance of contextualized representations on various natural language processing (NLP) tasks."

Czech name

—

Czech description

—

Type

O - Miscellaneous

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

—

Publication year

2023

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů