ArgLegalSumm: Improving Abstractive Summarization of Legal Documents with Argument Mining
This addresses the problem of generating better summaries for legal professionals by improving abstractive summarization, though it appears incremental.
The paper tackled the challenge of summarizing legal documents by integrating argument role labeling into the process, resulting in improved performance over strong baselines as shown in experiments with pretrained language models.
A challenging task when generating summaries of legal documents is the ability to address their argumentative nature. We introduce a simple technique to capture the argumentative structure of legal documents by integrating argument role labeling into the summarization process. Experiments with pretrained language models show that our proposed approach improves performance over strong baselines