Findings of the VarDial evaluation campaign 2023
This report presents the results of the shared tasks organized as part of the VarDial
Evaluation Campaign 2023. The campaign is part of the tenth workshop on Natural …
Evaluation Campaign 2023. The campaign is part of the tenth workshop on Natural …
A parallel corpus for Vietnamese central-northern dialect text transfer
T Le, A Luu - Findings of the Association for Computational …, 2023 - aclanthology.org
The Vietnamese language embodies dialectal variants closely attached to the nation's three
macro-regions: the Northern, Central and Southern regions. As the northern dialect forms …
macro-regions: the Northern, Central and Southern regions. As the northern dialect forms …
We're Calling an Intervention: Taking a Closer Look at Language Model Adaptation to Different Types of Linguistic Variation
A Srivastava, D Chiang - arXiv preprint arXiv:2404.07304, 2024 - arxiv.org
We present a suite of interventions and experiments that allow us to understand language
model adaptation to text with linguistic variation (eg, nonstandard or dialectal text). Our …
model adaptation to text with linguistic variation (eg, nonstandard or dialectal text). Our …
BERTwich: Extending BERT's Capabilities to Model Dialectal and Noisy Text
A Srivastava, D Chiang - Findings of the Association for …, 2023 - aclanthology.org
Real-world NLP applications often deal with nonstandard text (eg, dialectal, informal, or
misspelled text). However, language models like BERT deteriorate in the face of dialect …
misspelled text). However, language models like BERT deteriorate in the face of dialect …
Towards Equitable Natural Language Understanding Systems for Dialectal Cohorts: Debiasing Training Data
K Abboud, G Oz - Proceedings of the 2024 Joint International …, 2024 - aclanthology.org
Despite being widely spoken, dialectal variants of languages are frequently considered low
in resources due to lack of writing standards and orthographic inconsistencies. As a result …
in resources due to lack of writing standards and orthographic inconsistencies. As a result …