Adverbs, Surprisingly

Dmitry Nikolaev, Collin F. Baker, Miriam R. L. Petruck, Sebastian Padó

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

7 Downloads (Pure)

Abstract

This paper begins with the premise that adverbs are neglected in computational linguistics. This view derives from two analyses: a literature review and a novel adverb dataset to probe a state-of-the-art language model, thereby uncovering systematic gaps in accounts for adverb meaning. We suggest that using Frame Semantics for characterizing word meaning, as in FrameNet, provides a promising approach to adverb analysis, given its ability to describe ambiguity, semantic roles, and null instantiation.
Original languageEnglish
Title of host publicationProceedings of the 12th Joint Conference on Lexical and Computational Semantics (*SEM 2023)
Place of PublicationToronto, Canada
PublisherAssociation for Computational Linguistics
Pages512
Number of pages526
DOIs
Publication statusPublished - Jul 2023
Externally publishedYes
EventThe 12th Joint Conference on Lexical and Computational Semantics (*SEM 2023) - Toronto, Canada
Duration: 13 Jul 202314 Jul 2023
https://sites.google.com/view/starsem2023

Conference

ConferenceThe 12th Joint Conference on Lexical and Computational Semantics (*SEM 2023)
Country/TerritoryCanada
CityToronto
Period13/07/2314/07/23
Internet address

Keywords

  • cs.CL

Fingerprint

Dive into the research topics of 'Adverbs, Surprisingly'. Together they form a unique fingerprint.

Cite this