@inproceedings{hamster-2022-everybody,
title = "Everybody likes short sentences - A Data Analysis for the Text Complexity {DE} Challenge 2022",
author = "Hamster, Ulf A.",
editor = {M{\"o}ller, Sebastian and
Mohtaj, Salar and
Naderi, Babak},
booktitle = "Proceedings of the GermEval 2022 Workshop on Text Complexity Assessment of German Text",
month = sep,
year = "2022",
address = "Potsdam, Germany",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.germeval-1.2",
pages = "10--14",
abstract = "The German Text Complexity Assessment Shared Task in KONVENS 2022 explores how to predict a complexity score for sentence examples from language learners{'} perspective. Our modeling approach for this shared task utilizes off-the-shelf NLP tools for feature engineering and a Random Forest regression model. We identified the text length, or resp. the logarithm of a sentence{'}s string length, as the most important feature to predict the complexity score. Further analysis showed that the Pearson correlation between text length and complexity score is about $\rho$ {\mbox{$\approx$}} 0.777. A sensitivity analysis on the loss function revealed that semantic SBert features impact the complexity score as well.",
}
Markdown (Informal)
[Everybody likes short sentences - A Data Analysis for the Text Complexity DE Challenge 2022](https://aclanthology.org/2022.germeval-1.2) (Hamster, GermEval 2022)
ACL