# Divide and Generate: Neural Generation of Complex Sentences

## TL;DR

This paper introduces a neural method for transforming simple sentences into complex ones by dividing and generating clauses, improving the quality of generated sentences through a pipeline approach.

## Contribution

It presents a novel divide-and-generate framework for complex sentence creation and an automatic evaluation metric to assess model quality.

## Key findings

- Pipeline model outperforms end-to-end model in quality
- Automatic evaluation metric effectively estimates model performance
- Dividing sentences into clauses enhances generation accuracy

## Abstract

We propose a task to generate a complex sentence from a simple sentence in order to amplify various kinds of responses in the database. We first divide a complex sentence into a main clause and a subordinate clause to learn a generator model of modifiers, and then use the model to generate a modifier clause to create a complex sentence from a simple sentence. We present an automatic evaluation metric to estimate the quality of the models and show that a pipeline model outperforms an end-to-end model.