End-to-End Segmentation-based News Summarization
This addresses the need for more structured and detailed news summarization, though it is incremental as it builds on existing language models and summarization techniques.
The paper tackles the problem of digesting news content by introducing a segmentation-based summarization task, where a news article is divided into sections and each section is summarized, and demonstrates that their proposed model outperforms state-of-the-art sequence-to-sequence models on the new SegNews dataset.
In this paper, we bring a new way of digesting news content by introducing the task of segmenting a news article into multiple sections and generating the corresponding summary to each section. We make two contributions towards this new task. First, we create and make available a dataset, SegNews, consisting of 27k news articles with sections and aligned heading-style section summaries. Second, we propose a novel segmentation-based language generation model adapted from pre-trained language models that can jointly segment a document and produce the summary for each section. Experimental results on SegNews demonstrate that our model can outperform several state-of-the-art sequence-to-sequence generation models for this new task.