@inproceedings{34a62c1fb4344c5b963273c70aaf84e0,
title = "Comparing and Predicting Eye-tracking Data in Mandarin and Cantonese",
abstract = "Eye-tracking data in Chinese languages present unique challenges due to the non-alphabetic and unspaced nature of the Chinese writing systems. This paper introduces the first deeply-annotated joint Mandarin-Cantonese eye-tracking dataset, from which we achieve a unified eye-tracking prediction system for both language varieties. In addition to the commonly studied first fixation duration and the total fixation duration, this dataset also includes the second fixation duration, expressing fixation patterns that are more relevant to higher-level, structural processing. A basic comparison of the features and measurements in our dataset revealed variation between Mandarin and Cantonese on fixation patterns related to word class and word position. The test of feature usefulness suggested that traditional features are less powerful in predicting the second-pass fixation, to which the linear distance to root makes a leading contribution in Mandarin. In contrast, Cantonese eye-movement behavior relies more on word position and part of speech.",
author = "Junlin Li and Bo Peng and Hsu, {Yu Yin} and Emmanuele Chersoni",
note = "Publisher Copyright: {\textcopyright} 2023 Association for Computational Linguistics.; 10th Workshop on NLP for Similar Languages, Varieties and Dialects, VarDial 2023 ; Conference date: 05-05-2023",
year = "2023",
month = may,
language = "English",
series = "ACL 2023 - 10th Workshop on NLP for Similar Languages, Varieties and Dialects, VarDial 2023 - Proceedings of the Workshop",
publisher = "Association for Computational Linguistics (ACL)",
pages = "121--132",
editor = "Yves Scherrer and Tommi Jauhiainen and Nikola Ljubesic and Preslav Nakov and Jorg Tiedemann and Marcos Zampieri",
booktitle = "ACL 2023 - 10th Workshop on NLP for Similar Languages, Varieties and Dialects, VarDial 2023 - Proceedings of the Workshop",
address = "United States",
}