Data related to studying German discourse particle "ja" in translation equivalents.
@inproceedings{soubki-etal-2022-kojak,
title = "{KOJAK}: A New Corpus for Studying {G}erman Discourse Particle ja",
author = "Soubki, Adil and
Rambow, Owen and
Kang, Chong",
booktitle = "Proceedings of the 3rd Workshop on Computational Approaches to Discourse",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea and Online",
publisher = "International Conference on Computational Linguistics",
url = "https://aclanthology.org/2022.codi-1.1",
pages = "1--6",
abstract = "In German, ja can be used as a discourse particle to indicate that a proposition, according to the speaker, is believed by both the speaker and audience. We use this observation to create KoJaK, a distantly-labeled English dataset derived from Europarl for studying when a speaker believes a statement to be common ground. This corpus is then analyzed to identify lexical choices in English that correspond with German ja. Finally, we perform experiments on the dataset to predict if an English clause corresponds to a German clause containing ja and achieve an F-measure of 75.3{\%} on a balanced test corpus.",
}