Assessing the Significance of Encoded Information in Contextualized Representations to Word Sense Disambiguation

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3AVLA63KU3" target="_blank" >RIV/00216208:11320/25:VLA63KU3 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85189941578&partnerID=40&md5=044ea6803839540dee2289551e97f245" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85189941578&partnerID=40&md5=044ea6803839540dee2289551e97f245</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Assessing the Significance of Encoded Information in Contextualized Representations to Word Sense Disambiguation

Popis výsledku v původním jazyce

The similarity of representations is crucial for WSD. However, a lot of information is encoded in the contextualized representations, and it is not clear which sentence context features drive this similarity and whether these features are significant to WSD. In this study, we address these questions. First, we identify the sentence context features that are responsible for the similarity of the contextualized representations of different occurrences of words. For this purpose, we conduct an explainability experiment and identify the sentence context features that lead to the formation of the clusters in word sense clustering with CWEs. Then, we provide a qualitative evaluation for assessing the significance of these features to WSD. Our results show that features that lack significance to WSD determine the similarity of the representations even when different senses of a word occur in highly diverse contexts and sentence context provides clear clues for different senses. © 2024 UnImplicit 2024 - 3rd Workshop on Understanding Implicit and Underspecified Language, Proceedings of the Workshop. All rights reserved.

Název v anglickém jazyce

Assessing the Significance of Encoded Information in Contextualized Representations to Word Sense Disambiguation

Popis výsledku anglicky

The similarity of representations is crucial for WSD. However, a lot of information is encoded in the contextualized representations, and it is not clear which sentence context features drive this similarity and whether these features are significant to WSD. In this study, we address these questions. First, we identify the sentence context features that are responsible for the similarity of the contextualized representations of different occurrences of words. For this purpose, we conduct an explainability experiment and identify the sentence context features that lead to the formation of the clusters in word sense clustering with CWEs. Then, we provide a qualitative evaluation for assessing the significance of these features to WSD. Our results show that features that lack significance to WSD determine the similarity of the representations even when different senses of a word occur in highly diverse contexts and sentence context provides clear clues for different senses. © 2024 UnImplicit 2024 - 3rd Workshop on Understanding Implicit and Underspecified Language, Proceedings of the Workshop. All rights reserved.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

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

Projekt

—

Návaznosti

—

Rok uplatnění

2024

Kód důvěrnosti údajů

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

Název statě ve sborníku

UnImplicit - Workshop Underst. Implicit Underspecified Lang., Proc. Workshop

ISBN

979-889176083-7

ISSN

—

e-ISSN

—

Počet stran výsledku

12

Strana od-do

42-53

Název nakladatele

Association for Computational Linguistics (ACL)

Místo vydání

—

Místo konání akce

St. Julian's

Datum konání akce

1. 1. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—