Comparing styles across languages
S Havaldar, M Pressimone, E Wong… - arXiv preprint arXiv …, 2023 - arxiv.org
Understanding how styles differ across languages is advantageous for training both humans
and computers to generate culturally appropriate text. We introduce an explanation …
and computers to generate culturally appropriate text. We introduce an explanation …
Extracting Lexical Features from Dialects via Interpretable Dialect Classifiers
Identifying linguistic differences between dialects of a language often requires expert
knowledge and meticulous human analysis. This is largely due to the complexity and …
knowledge and meticulous human analysis. This is largely due to the complexity and …
A Comparative Study on Textual Saliency of Styles from Eye Tracking, Annotations, and Language Models
K De Langis, D Kang - arXiv preprint arXiv:2212.09873, 2022 - arxiv.org
There is growing interest in incorporating eye-tracking data and other implicit measures of
human language processing into natural language processing (NLP) pipelines. The data …
human language processing into natural language processing (NLP) pipelines. The data …
BERT, but Better: Improving Robustness using Human Insights
M Pieke - 2023 - studenttheses.uu.nl
Pre-trained transformers are highly effective across numerous Natural Language Processing
(NLP) tasks, yet their ability to generalise to new domains remains a concern due to their …
(NLP) tasks, yet their ability to generalise to new domains remains a concern due to their …