Towards Single Word Lexical Complexity Prediction

David Alfter, Elena Volodina


Abstract
In this paper we present work-in-progress where we investigate the usefulness of previously created word lists to the task of single-word lexical complexity analysis and prediction of the complexity level for learners of Swedish as a second language. The word lists used map each word to a single CEFR level, and the task consists of predicting CEFR levels for unseen words. In contrast to previous work on word-level lexical complexity, we experiment with topics as additional features and show that linking words to topics significantly increases accuracy of classification.
Anthology ID:
W18-0508
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:
79–88
Language:
URL:
https://www.aclweb.org/anthology/W18-0508
DOI:
10.18653/v1/W18-0508
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/W18-0508.pdf