Summarization with Precise Length Control
This addresses the need for precise length control in summarization applications, offering an incremental improvement over existing methods that degrade performance or provide only approximate control.
The paper tackles the problem of generating text summaries with exact length control, presenting a framework that maintains or improves quality while precisely meeting token or sentence count targets, and demonstrates improved performance on the CNNDM dataset.
Many applications of text generation such as summarization benefit from accurately controlling the text length. Existing approaches on length-controlled summarization either result in degraded performance or can only control the length approximately. In this work, we present a framework to generate summaries with precisely the specified number of tokens or sentences, while maintaining or even improving the text quality. In addition, we jointly train the models to predict the lengths, so our model can generate summaries with optimal length. We evaluate the proposed framework on the CNNDM dataset and show improved performance compared to existing methods.