Sentence Simplification with Deep Reinforcement Learning
TL
TL;DR
This work addresses the simplification problem with an encoder-decoder model coupled with a deep reinforcement learning framework, and explores the space of possible simplifications while learning to optimize a reward function that encourages outputs which are simple, fluent, and preserve the meaning of the input.
Abstract
Sentence simplification aims to make sentences easier to read and understand. Most recent approaches draw on insights from machine translation to learn simplification rewrites from monolingual corpora of complex and simple sentences. We address the simplification problem with an encoder-decoder model coupled with a deep reinforcement learning framework. Our model, which we call DRESS (as shorthand for Deep REinforcement Sentence Simplification), explores the space of possible simplifications while learning to optimize a reward function that encourages outputs which are simple, fluent, and preserve the meaning of the input. Experiments on three datasets demonstrate that our model outperforms competitive simplification systems.
References52 items
1
Optimizing Statistical Machine Translation for Text Simplification
2
Deep Reinforcement Learning for Dialogue Generation
3
Abstractive Sentence Summarization with Attentive Recurrent Neural Networks
4
Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning
5