Sentence Simplification with Memory-Augmented Neural Networks
This work addresses sentence simplification for NLP applications and human readers, but it is incremental as it adapts an existing architecture to a new task.
The paper tackled sentence simplification by adapting a memory-augmented neural network architecture, achieving effectiveness on multiple datasets as measured by automatic metrics and human judgments.
Sentence simplification aims to simplify the content and structure of complex sentences, and thus make them easier to interpret for human readers, and easier to process for downstream NLP applications. Recent advances in neural machine translation have paved the way for novel approaches to the task. In this paper, we adapt an architecture with augmented memory capacities called Neural Semantic Encoders (Munkhdalai and Yu, 2017) for sentence simplification. Our experiments demonstrate the effectiveness of our approach on different simplification datasets, both in terms of automatic evaluation measures and human judgments.