BillSum: A Corpus for Automatic Summarization of US Legislation

By Anastassia Kornilova, Vladimir Eidelman. 2019

209 citations recorded by the source corpus.

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. 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 billa, thus, showing that methods developed on this dataset can transfer to states without human-written summaries.

Subfields: Artificial Intelligence, Natural Language Processing, Evaluation & Benchmarks

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

In Evaluation & Benchmarks

Citations in the corpus

PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization (2019, background): “BillSum (Kornilova and Eidelman, 2019) contains 23k US Congressional bills and humanwritten reference summaries from the 103rd-115th (1993-2018) sessions of Congress.”
LongForm: Effective Instruction Tuning with Reverse Instructions (2023, neutral): “They cover a diverse range of topics, including events, careers, biographies, and writing tasks such as reviews, summaries and essays – and this is just looking at the 11% of our LongForm-C dataset with reverse instructions (RI).”
Planning with Learned Entity Prompts for Abstractive Summarization (2021, background): “Inputs and outputs were truncated to 512 and 128 for XSum and SAMSum, and 1024 and 256 for CNN/DailyMail and BillSum.”
Efficient Attentions for Long Document Summarization (2021, background): “, 2018) that consist of scientific publications; BILLSUM (Kornilova and Eidelman, 2019), a collection of congressional bills; and BIGPATENT (Sharma et al.”
A Dataset for Statutory Reasoning in Tax Law Entailment and Question Answering (2020, unknown): “The intersection between NLP and the legal domain is a growing area of research [3, 10, 19, 33, 47], but with few large-scale systematic resources.”
SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization (2021, background): “Recent efforts to expand the application of summarization to new domains such as legal (Kornilova and Eidelman, 2019) or scholarly (Cachola et al.”