Skip to Main content Skip to Navigation
Conference papers

About Time: Do Transformers Learn Temporal Verbal Aspect?

Abstract : 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. We perform experiments in English and French, and our results show that transformer models adequately capture information on telicity and duration in their vectors, even in their non-finetuned forms, but are somewhat biased with regard to verb tense and word order.
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03699336
Contributor : Nabil Hathout Connect in order to contact the contributor
Submitted on : Monday, June 20, 2022 - 11:06:51 AM
Last modification on : Monday, July 4, 2022 - 9:45:21 AM

File

Hathout-2022-CMCL.pdf
Publisher files allowed on an open archive

Identifiers

Citation

Eleni Metheniti, Tim van de Cruys, Nabil Hathout. About Time: Do Transformers Learn Temporal Verbal Aspect?. 12th Workshop on Cognitive Modeling and Computational Linguistics (CMCL 2022), May 2022, Dublin, Ireland. pp.88-101, ⟨10.18653/v1/2022.cmcl-1.10⟩. ⟨hal-03699336⟩

Share

Metrics

Record views

17

Files downloads

1