Paper: Sentence Simplification by Monolingual Machine Translation

ACL ID P12-1107
Title Sentence Simplification by Monolingual Machine Translation
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2012

In this paper we describe a method for simpli- fying sentences using Phrase Based Machine Translation, augmented with a re-ranking heuristic based on dissimilarity, and trained on a monolingual parallel corpus. We compare our system to a word-substitution baseline and two state-of-the-art systems, all trained and tested on paired sentences from the English part of Wikipedia and Simple Wikipedia. Hu- man test subjects judge the output of the dif- ferent systems. Analysing the judgements shows that by relatively careful phrase-based paraphrasing our model achieves similar sim- plification results to state-of-the-art systems, while generating better formed output. We also argue that text readability metrics such as the Flesch-Kincaid grade level should be used with caution when evaluating the...