← Search

Ekaterina Garmash

1 accepted papers

2023

Connecting degree and polarity: An artificial language learning study

EMNLP 2023long main

We investigate a new linguistic generalisation in pre-trained language models (taking BERT Devlin et al. 2019 as a case study). We focus on degree modifiers (expressions like slightly, very, rather, extremely) and test the hypothesis that the degree expressed by a modifier (low, medium or high degre…

Cited by 0SourcecodeScholar