EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Findings of EACL 2023

Andreas Vlachos (Redaktør), Isabelle Augenstein (Redaktør)

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningpeer review

10 Downloads (Pure)

Abstract

The proceedings contain 196 papers. The topics discussed include: using punctuation as an adversarial attack on deep learning-based NLP systems: an empirical study; self-supervised unimodal label generation strategy using recalibrated modality representations for multimodal sentiment analysis; improving numeracy by input reframing and quantitative pre-finetuning task; visualize before you write: imagination-guided open-ended text generation; entity-aware dual co-attention network for fake news detection; data-efficient methods for improving hate speech detection; learning the effects of physical actions in a multi-modal environment; revisiting intermediate layer distillation for compressing language models: an overfitting perspective; implicit temporal reasoning for evidence-based fact-checking; translate first reorder later: leveraging monotonicity in semantic parsing; and infusing context and knowledge awareness in multi-turn dialog understanding.

OriginalsprogEngelsk
TitelFindings of the Association for Computational Linguistics: EACL 2023
ForlagAssociation for Computational Linguistics (ACL)
Publikationsdato2023
ISBN (Elektronisk)9781959429470
StatusUdgivet - 2023
Begivenhed17th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2023 - Findings of EACL 2023 - Dubrovnik, Kroatien
Varighed: 2 maj 20236 maj 2023

Konference

Konference17th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2023 - Findings of EACL 2023
Land/OmrådeKroatien
ByDubrovnik
Periode02/05/202306/05/2023
SponsorAdobe, Babelscape, Bloomberg Engineering, Duolingo, Liveperson

Citationsformater