Estimating Linguistic Complexity for Science Texts

Farah Nadeem, Mari Ostendorf


Abstract
Evaluation of text difficulty is important both for downstream tasks like text simplification, and for supporting educators in classrooms. Existing work on automated text complexity analysis uses linear models with engineered knowledge-driven features as inputs. While this offers interpretability, these models have lower accuracy for shorter texts. Traditional readability metrics have the additional drawback of not generalizing to informational texts such as science. We propose a neural approach, training on science and other informational texts, to mitigate both problems. Our results show that neural methods outperform knowledge-based linear models for short texts, and have the capacity to generalize to genres not present in the training data.
Anthology ID:
W18-0505
Volume:
Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications
Month:
June
Year:
2018
Address:
New Orleans, Louisiana
Venues:
BEA | NAACL | WS
SIG:
SIGEDU
Publisher:
Association for Computational Linguistics
Note:
Pages:
45–55
Language:
URL:
https://www.aclweb.org/anthology/W18-0505
DOI:
10.18653/v1/W18-0505
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/W18-0505.pdf