Controlling Output Length in Neural Encoder-Decoders

Yuta Kikuchi1, Graham Neubig2, Ryohei Sasano1, Hiroya Takamura1, Manabu Okumura1
1Tokyo Institute of Technology, 2Carnegie Mellon University


Abstract

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 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.