Compositionality and Event Retrieval in Complement Coercion: A Study of Language Models in a Low-resource Setting

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

Abstract

In sentences such as John began the book, the complement noun, lexically denoting an entity, is interpreted as an event. This phenomenon is known in linguistics as complement coercion: the event associated with the verb is not overtly expressed but can be recovered from the meanings of other constituents, context and world knowledge. We investigate whether language models (LMs) can exploit sentence structure and compositional meaning to recover plausible events in complement coercion. For the first time, we tested different LMs in Norwegian, a low-resource language with high syntactic variation in coercion constructions across aspectual verbs. Results reveal that LMs struggle with retrieving plausible events and with ranking them above less plausible ones. Moreover, we found that LMs do not exploit the compositional properties of coercion sentences in their predictions.
Original languageEnglish
Title of host publicationProceedings of the 29th Conference on Computational Natural Language Learning (CoNLL 2025)
EditorsGemma Boleda, Michael Roth
PublisherAssociation for Computational Linguistics
Pages469-480
ISBN (Electronic)9798891762718
Publication statusPublished - Jul 2025
EventConference on Natural Language Learning - Austria Center Vienna, Vienna, Austria
Duration: 31 Jul 20251 Aug 2025
https://www.conll.org/

Competition

CompetitionConference on Natural Language Learning
Abbreviated titleCONLL 2025
Country/TerritoryAustria
CityVienna
Period31/07/251/08/25
Internet address

Fingerprint

Dive into the research topics of 'Compositionality and Event Retrieval in Complement Coercion: A Study of Language Models in a Low-resource Setting'. Together they form a unique fingerprint.

Cite this