BillSum: A Corpus for Automatic Summarization of US Legislation
This addresses the problem of processing large volumes of legislative text for policymakers and researchers, though it is incremental as it applies existing summarization methods to a new domain.
The authors tackled the lack of a dataset for automatic summarization of US legislation by introducing BillSum, the first corpus for Congressional and California state bills, and benchmarked extractive methods, showing that models trained on Congressional bills can transfer to summarize California bills with no human-written summaries.
Automatic summarization methods have been studied on a variety of domains, including news and scientific articles. Yet, legislation has not previously been considered for this task, despite US Congress and state governments releasing tens of thousands of bills every year. In this paper, we introduce BillSum, the first dataset for summarization of US Congressional and California state bills (https://github.com/FiscalNote/BillSum). We explain the properties of the dataset that make it more challenging to process than other domains. Then, we benchmark extractive methods that consider neural sentence representations and traditional contextual features. Finally, we demonstrate that models built on Congressional bills can be used to summarize California bills, thus, showing that methods developed on this dataset can transfer to states without human-written summaries.