Show simple item record

dc.contributor.authorVulic, Ivanen
dc.contributor.authorPonti, Edoardoen
dc.contributor.authorLitschko, Roberten
dc.contributor.authorGlavas, Goranen
dc.contributor.authorKorhonen, Annaen
dc.date.accessioned2020-12-15T00:31:51Z
dc.date.available2020-12-15T00:31:51Z
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/315105
dc.description.abstractThe success of large pretrained language models (LMs) such as BERT and RoBERTa has sparked interest in probing their representations, in order to unveil what types of knowledge they implicitly capture. While prior research focused on morphosyntactic, semantic, and world knowledge, it remains unclear to which extent LMs also derive lexical type-level knowledge from words in context. In this work, we present a systematic empirical analysis across six typologically diverse languages and five different lexical tasks, addressing the following questions: 1) How do different lexical knowledge extraction strategies (monolingual versus multilingual source LM, out-of-context versus in-context encoding, inclusion of special tokens, and layer-wise averaging) impact performance? How consistent are the observed effects across tasks and languages? 2) Is lexical knowledge stored in few parameters, or is it scattered throughout the network? 3) How do these representations fare against traditional static word vectors in lexical tasks? 4) Does the lexical information emerging from independently trained monolingual LMs display latent similarities? Our main results indicate patterns and best practices that hold universally, but also point to prominent variations across languages and tasks. Moreover, we validate the claim that lower Transformer layers carry more type-level lexical knowledge, but also show that this knowledge is distributed across multiple layers.
dc.publisherAssociation for Computational Linguistics
dc.rightsAll rights reserved
dc.rights.uri
dc.titleProbing Pretrained Language Models for Lexical Semanticsen
dc.typeConference Object
prism.publicationNameProceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2020)en
dc.identifier.doi10.17863/CAM.62212
dcterms.dateAccepted2020-09-15en
rioxxterms.versionofrecord10.18653/v1/2020.emnlp-main.586en
rioxxterms.versionVoR
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserveden
rioxxterms.licenseref.startdate2020-09-15en
rioxxterms.typeConference Paper/Proceeding/Abstracten
pubs.funder-project-idECH2020 EUROPEAN RESEARCH COUNCIL (ERC) (648909)
pubs.conference-nameConference on Empirical Methods in Natural Language Processing (EMNLP 2020)en
pubs.conference-start-date2020-11-16en


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record