Controlling Output Length in Neural Encoder-Decoders

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 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.

11 pages. To appear in EMNLP 2016

Cited by in corpus (12)

• Explaining Question Answering Models through Text Generation
• Controlling the Output Length of Neural Machine Translation
• Deep Recurrent Generative Decoder for Abstractive Text Summarization
• Length-controllable Abstractive Summarization by Guiding with Summary Prototype
• Steering Output Style and Topic in Neural Response Generation
• Deep Extrapolation for Attribute-Enhanced Generation
• Positional Encoding to Control Output Sequence Length
• Neural Rule-Execution Tracking Machine For Transformer-Based Text Generation
• LenAtten: An Effective Length Controlling Unit For Text Summarization
• Controlling Length in Image Captioning
• An Empirical Study of Extrapolation in Text Generation with Scalar Control
• CUT: Controllable Unsupervised Text Simplification