About Time: Do Transformers Learn Temporal Verbal Aspect?
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11210%2F22%3A10456696" target="_blank" >RIV/00216208:11210/22:10456696 - isvavai.cz</a>
Výsledek na webu
<a href="https://doi.org/10.18653/v1/2022.cmcl-1.10" target="_blank" >https://doi.org/10.18653/v1/2022.cmcl-1.10</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.18653/v1/2022.cmcl-1.10" target="_blank" >10.18653/v1/2022.cmcl-1.10</a>
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
About Time: Do Transformers Learn Temporal Verbal Aspect?
Popis výsledku v původním jazyce
Aspect is a linguistic concept that describes how an action, event, or state of a verb phrase is situated in time. In this paper, we explore whether different transformer models are capable of identifying aspectual features. We focus on two specific aspectual features: telicity and duration. Telicity marks whether the verb's action or state has an endpoint or not (telic/atelic), and duration denotes whether a verb expresses an action (dynamic) or a state (stative). These features are integral to the interpretation of natural language, but also hard to annotate and identify with NLP methods. Our results show that transformer models adequately capture information on telicity and duration in their vectors, even in their pretrained forms, but are somewhat biased with regard to verb tense and word order.
Název v anglickém jazyce
About Time: Do Transformers Learn Temporal Verbal Aspect?
Popis výsledku anglicky
Aspect is a linguistic concept that describes how an action, event, or state of a verb phrase is situated in time. In this paper, we explore whether different transformer models are capable of identifying aspectual features. We focus on two specific aspectual features: telicity and duration. Telicity marks whether the verb's action or state has an endpoint or not (telic/atelic), and duration denotes whether a verb expresses an action (dynamic) or a state (stative). These features are integral to the interpretation of natural language, but also hard to annotate and identify with NLP methods. Our results show that transformer models adequately capture information on telicity and duration in their vectors, even in their pretrained forms, but are somewhat biased with regard to verb tense and word order.
Klasifikace
Druh
O - Ostatní výsledky
CEP obor
—
OECD FORD obor
60203 - Linguistics
Návaznosti výsledku
Projekt
—
Návaznosti
—
Ostatní
Rok uplatnění
2022
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů