Posgram Driven Word Prediction

Carmelo Spiccia, Agnese Augello, Giovanni Pilato

2015

Abstract

Several word prediction algorithms have been described in literature for automatic sentence completion from a finite candidate words set. However, at the best of our knowledge, very little or no work has been done on reducing the cardinality of this set. To address this issue, we use posgrams to predict the part of speech of the missing word first. Candidate words are then restricted to the ones fulfilling the predicted part of speech. We show how this additional step can improve the processing speed and the accuracy of word predictors. Experimental results are provided for the Italian language.

Paper Citation

in Harvard Style

Spiccia C., Augello A. and Pilato G. (2015). Posgram Driven Word Prediction . In Proceedings of the 7th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: DART, (IC3K 2015) ISBN 978-989-758-158-8, pages 589-596. DOI: 10.5220/0005613305890596

in Bibtex Style

@conference{dart15,
author={Carmelo Spiccia and Agnese Augello and Giovanni Pilato},
title={Posgram Driven Word Prediction},
booktitle={Proceedings of the 7th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: DART, (IC3K 2015)},
year={2015},
pages={589-596},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005613305890596},
isbn={978-989-758-158-8},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 7th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: DART, (IC3K 2015)
TI - Posgram Driven Word Prediction
SN - 978-989-758-158-8
AU - Spiccia C.
AU - Augello A.
AU - Pilato G.
PY - 2015
SP - 589
EP - 596
DO - 10.5220/0005613305890596