Length-controllable Abstractive Summarization by Guiding with Summary Prototype

TL;DR

This paper introduces a length-controllable abstractive summarization model that uses a word-level extractive module to generate summaries aligned with specified length constraints, outperforming previous methods.

Contribution

The novel approach incorporates a prototype text extracted from the source to guide length-controlled summarization, unlike previous length embedding methods.

Findings

Outperforms previous models in length-controlled summarization tasks.

Effective in generating informative summaries adhering to length constraints.

Demonstrates robustness across CNN/Daily Mail and NEWSROOM datasets.

Abstract

We propose a new length-controllable abstractive summarization model. Recent state-of-the-art abstractive summarization models based on encoder-decoder models generate only one summary per source text. However, controllable summarization, especially of the length, is an important aspect for practical applications. Previous studies on length-controllable abstractive summarization incorporate length embeddings in the decoder module for controlling the summary length. Although the length embeddings can control where to stop decoding, they do not decide which information should be included in the summary within the length constraint. Unlike the previous models, our length-controllable abstractive summarization model incorporates a word-level extractive module in the encoder-decoder model instead of length embeddings. Our model generates a summary in two steps. First, our word-level extractor extracts a sequence of important words (we call it the "prototype text") from the source text according to the word-level importance scores and the length constraint. Second, the prototype text is used as additional input to the encoder-decoder model, which generates a summary by jointly encoding and copying words from both the prototype text and source text. Since the prototype text is a guide to both the content and length of the summary, our model can generate an informative and length-controlled summary. Experiments with the CNN/Daily Mail dataset and the NEWSROOM dataset show that our model outperformed previous models in length-controlled settings.