An Experimental Study of LSTM Encoder-Decoder Model for Text Simplification

TL;DR

This paper explores using an LSTM Encoder-Decoder neural network for text simplification, demonstrating its ability to learn basic sequence operations and potentially modify sentence structure and vocabulary.

Contribution

It introduces the application of LSTM Encoder-Decoder models to text simplification, highlighting their capacity to learn rule-like transformations from sequence pairs.

Findings

LSTM Encoder-Decoder can learn reversing, sorting, and replacing operations.

The model shows potential to modify sentence structure and vocabulary for simplification.

Preliminary results suggest applicability to text simplification tasks.

Abstract

Text simplification (TS) aims to reduce the lexical and structural complexity of a text, while still retaining the semantic meaning. Current automatic TS techniques are limited to either lexical-level applications or manually defining a large amount of rules. Since deep neural networks are powerful models that have achieved excellent performance over many difficult tasks, in this paper, we propose to use the Long Short-Term Memory (LSTM) Encoder-Decoder model for sentence level TS, which makes minimal assumptions about word sequence. We conduct preliminary experiments to find that the model is able to learn operation rules such as reversing, sorting and replacing from sequence pairs, which shows that the model may potentially discover and apply rules such as modifying sentence structure, substituting words, and removing words for TS.