Cargando…
Shapley Idioms: Analysing BERT Sentence Embeddings for General Idiom Token Identification
This article examines the basis of Natural Language Understanding of transformer based language models, such as BERT. It does this through a case study on idiom token classification. We use idiom token identification as a basis for our analysis because of the variety of information types that have p...
Autores principales: | Nedumpozhimana, Vasudevan, Klubička, Filip, Kelleher, John D. |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8964145/ https://www.ncbi.nlm.nih.gov/pubmed/35360661 http://dx.doi.org/10.3389/frai.2022.813967 |
Ejemplares similares
-
MeaningBERT: assessing meaning preservation between sentences
por: Beauchemin, David, et al.
Publicado: (2023) -
Sentence-level complexity in Russian: An evaluation of BERT and graph neural networks
por: Ivanov, Vladimir Vladimirovich
Publicado: (2022) -
Stance detection with BERT embeddings for credibility analysis of information on social media
por: Karande, Hema, et al.
Publicado: (2021) -
Idioms of Distress
por: Desai, Geetha, et al.
Publicado: (2017) -
Unsupervised online multitask learning of behavioral sentence embeddings
por: Tseng, Shao-Yen, et al.
Publicado: (2019)