@inproceedings{agirrezabal-etal-2023-hidden,
title = "The Hidden Folk: Linguistic Properties Encoded in Multilingual Contextual Character Representations",
author = "Agirrezabal, Manex and
Boldsen, Sidsel and
Hollenstein, Nora",
editor = "Gorman, Kyle and
Sproat, Richard and
Roark, Brian",
booktitle = "Proceedings of the Workshop on Computation and Written Language (CAWL 2023)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.cawl-1.2",
doi = "10.18653/v1/2023.cawl-1.2",
pages = "6--13",
abstract = "To gain a better understanding of the linguistic information encoded in character-based language models, we probe the multilingual contextual CANINE model. We design a range of phonetic probing tasks in six Nordic languages, including Faroese as an additional zero-shot instance. We observe that some phonetic information is indeed encoded in the character representations, as consonants and vowels can be well distinguished using a linear classifier. Furthermore, results for the Danish and Norwegian language seem to be worse for the consonant/vowel distinction in comparison to other languages. The information encoded in these representations can also be learned in a zero-shot scenario, as Faroese shows a reasonably good performance in the same vowel/consonant distinction task.",
}
Markdown (Informal)
[The Hidden Folk: Linguistic Properties Encoded in Multilingual Contextual Character Representations](https://aclanthology.org/2023.cawl-1.2) (Agirrezabal et al., CAWL 2023)
ACL