Show simple item record

dc.contributor.authorArdanuy, MCen_US
dc.contributor.authorNanni, Fen_US
dc.contributor.authorBeelen, Ken_US
dc.contributor.authorHosseini, Ken_US
dc.contributor.authorAhnert, Ren_US
dc.contributor.authorLawrence, Jen_US
dc.contributor.authorMcDonough, Ken_US
dc.contributor.authorTolfo, Gen_US
dc.contributor.authorWilson, DCSen_US
dc.contributor.authorMcGillivray, Ben_US
dc.date.accessioned2020-06-22T13:33:17Z
dc.identifier.urihttps://qmro.qmul.ac.uk/xmlui/handle/123456789/65109
dc.description13 pages, 2 figuresen_US
dc.description13 pages, 2 figuresen_US
dc.description13 pages, 2 figuresen_US
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 upon 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.en_US
dc.subjectcs.CLen_US
dc.subjectcs.CLen_US
dc.titleLiving Machines: A study of atypical animacyen_US
dc.typeArticle
pubs.author-urlhttp://arxiv.org/abs/2005.11140v1en_US
pubs.notesNot knownen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record