LAST在CMCL 2021共享任务中的工作：基于梯度提升决策树方法预测阅读时的眼动数据
计算与语言
2021-04-28 v1
摘要
针对2021年CMCL眼动数据预测共享任务，我们对一个以目标词词汇特征以及从词频列表、心理测量数据和双字关联度量中获取的特征为输入的LightGBM模型进行了优化。该模型在需预测的五种眼动指标中的两项上取得了所有团队中的最佳性能，使其在官方挑战准则上排名第一，并优于参与该挑战的所有基于深度学习的系统。
引用
@article{arxiv.2104.13043,
title = {LAST at CMCL 2021 Shared Task: Predicting Gaze Data During Reading with a Gradient Boosting Decision Tree Approach},
author = {Yves Bestgen},
journal= {arXiv preprint arXiv:2104.13043},
year = {2021}
}
备注
To be published in the Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics, co-located with NAACL 2021 in Mexico City, Mexico (virtual), on the 10th of June 2021