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.
@article{arxiv.1901.10196,
title = {Divide and Generate: Neural Generation of Complex Sentences},
author = {Tomoya Ogata and Mamoru Komachi and Tomoya Takatani},
journal= {arXiv preprint arXiv:1901.10196},
year = {2019}
}