Improving text simplification by corpus expansion with unsupervised learning
Akihiro Katsuta, Kazuhide Yamamoto · 2019
Automatic sentence simplification aims to reduce the complexity of vocabulary and expressions in a sentence while retaining its original meaning. We constructed a simplification model that does not require a parallel corpus using an unsupervised translation model. In order to learn simplification by unsupervised manner, we show that pseudo-corpus is constructed from the web corpus and that the corpus expansion contributes to output more simplified sentences. In addition, we confirm that it is possible to learn the operation of simplification by preparing large-scale pseudo data even if there is non-parallel corpus for simplification.