Show simple item record

dc.contributor.authorColl Ardanuy, Marionaen
dc.contributor.authorNanni, Federicoen
dc.contributor.authorBeelen, Kasparen
dc.contributor.authorHosseini, Kasraen
dc.contributor.authorAhnert, Ruthen
dc.contributor.authorLawrence, Jonen
dc.contributor.authorMcDonough, Katherineen
dc.contributor.authorTolfo, Giorgiaen
dc.contributor.authorWilson, Daniel CSen
dc.contributor.authorMcGillivray, Barbaraen
dc.date.accessioned2021-01-08T00:31:58Z
dc.date.available2021-01-08T00:31:58Z
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/315895
dc.description.abstractThis paper proposes a new approach to animacy detection, the task of determining whether an entity is represented as animate in a text. In particular, this work is focused on atypical animacy and examines the scenario in which typically inanimate objects, specifically machines, are given animate attributes. To address it, we have created the first dataset for atypical animacy detection, based on nineteenth-century sentences in English, with machines represented as either animate or inanimate. Our method builds on recent innovations in language modeling, specifically BERT contextualized word embeddings, to better capture fine-grained contextual properties of words. We present a fully unsupervised pipeline, which can be easily adapted to different contexts, and report its performance on an established animacy dataset and our newly introduced resource. We show that our method provides a substantially more accurate characterization of atypical animacy, especially when applied to highly complex forms of language use.
dc.rightsAll rights reserved
dc.rights.uri
dc.titleLiving Machines: A study of atypical animacyen
dc.typeConference Object
prism.publicationNameProceedings of the 28th International Conference on Computational Linguisticsen
dc.identifier.doi10.17863/CAM.63006
dcterms.dateAccepted2020-10-30en
rioxxterms.versionVoR
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserveden
rioxxterms.licenseref.startdate2020-10-30en
dc.contributor.orcidMcGillivray, Barbara [0000-0003-3426-8200]
rioxxterms.typeConference Paper/Proceeding/Abstracten
pubs.funder-project-idAlan Turing Institute (EP/N510129/1)
dc.identifier.urlhttps://www.aclweb.org/anthology/events/coling-2020/#2020-coling-mainen
pubs.conference-name28th International Conference on Computational Linguistics (COLING 2020)en
pubs.conference-start-date2020-12-08en


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record