Unsupervised Sentence Simplification Using Deep Semantics
This addresses the problem of simplifying sentences for accessibility or readability, offering an unsupervised alternative to supervised methods.
The paper tackles sentence simplification without needing hand-written rules or aligned training data, using deep semantic structure for sentence splitting, and shows its unsupervised framework is competitive with four state-of-the-art supervised systems.
We present a novel approach to sentence simplification which departs from previous work in two main ways. First, it requires neither hand written rules nor a training corpus of aligned standard and simplified sentences. Second, sentence splitting operates on deep semantic structure. We show (i) that the unsupervised framework we propose is competitive with four state-of-the-art supervised systems and (ii) that our semantic based approach allows for a principled and effective handling of sentence splitting.