Neural encoder-decoder models have shown great success in many sequence generation tasks. However, previous work has not investigated situations in which we would like to control the length of encoder-decoder outputs. This capability is crucial for applications such as text summarization, in which we have to generate concise summaries with a desired length. In this paper, we propose methods for controlling the output sequence length for neural encoder-decoder models: two decoding-based methods and two learning-based methods. Results show that our learning-based methods have the capability to control length without degrading summary quality in a summarization task.
@article{arxiv.1609.09552,
title = {Controlling Output Length in Neural Encoder-Decoders},
author = {Yuta Kikuchi and Graham Neubig and Ryohei Sasano and Hiroya Takamura and Manabu Okumura},
journal= {arXiv preprint arXiv:1609.09552},
year = {2016}
}