Unsupervised Sentence Simplification via Dependency Parsing
This work addresses the problem of making text more readable and understandable, particularly for applications like accessibility or language learning, with an incremental improvement in unsupervised methods.
The paper tackles unsupervised sentence simplification by using dependency parsing and sentence embeddings to produce linguistically effective simplifications, achieving a state-of-the-art SARI score of 39.13 on the TurkCorpus set and competitive performance against supervised baselines.
Text simplification is the task of rewriting a text so that it is readable and easily understood. In this paper, we propose a simple yet novel unsupervised sentence simplification system that harnesses parsing structures together with sentence embeddings to produce linguistically effective simplifications. This means our model is capable of introducing substantial modifications to simplify a sentence while maintaining its original semantics and adequate fluency. We establish the unsupervised state-of-the-art at 39.13 SARI on TurkCorpus set and perform competitively against supervised baselines on various quality metrics. Furthermore, we demonstrate our framework's extensibility to other languages via a proof-of-concept on Vietnamese data. Code for reproduction is published at \url{https://github.com/isVy08/USDP}.