All mixed up Finding the optimal feature set for general readability prediction and its application to English and DutchReport as inadecuate




All mixed up Finding the optimal feature set for general readability prediction and its application to English and Dutch - Download this document for free, or read online. Document in PDF available to download.

(2016)COMPUTATIONAL LINGUISTICS.42(3).p.457-490 Mark abstract Readability research has a long and rich tradition, but there has been too little focus on general readability prediction without targeting a specific audience or text genre. Moreover, though NLP-inspired research has focused on adding more complex readability features there is still no consensus on which features contribute most to the prediction. In this article, we investigate in close detail the feasibility of constructing a readability prediction system for English and Dutch generic text using supervised machine learning. Based on readability assessments by both expertsand a crowd, we implement different types of text characteristics ranging from easy-to-compute superficial text characteristics to features requiring a deep linguistic processing, resulting in tendifferent feature groups. Both a regression and classification setup are investigated reflecting the two possible readability prediction tasks: scoring individual texts or comparing two texts. We show that going beyond correlation calculations for readability optimization using a wrapper-based genetic algorithm optimization approach is a promising task which provides considerable insights in which feature combinations contribute to the overall readability prediction. Since we also have gold standard information available for those features requiring deep processing we are able to investigate the true upper bound of our Dutch system. Interestingly, we will observe that the performance of our fully-automatic readability prediction pipeline is on par with the pipeline using golden deep syntactic and semantic information.

Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-7175390



Author: Orphée De Clercq and Veronique Hoste

Source: https://biblio.ugent.be/publication/7175390



DOWNLOAD PDF




Related documents