Controlling Output Length in Neural Encoder-Decoders
This addresses a crucial need for applications like text summarization, where generating concise summaries of desired lengths is important, representing an incremental improvement over existing models.
The paper tackles the problem of controlling output sequence length in neural encoder-decoder models, proposing two decoding-based and two learning-based methods, with results showing that the learning-based methods can control length without degrading summary quality in a summarization task.
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.