Instruction-Guided Bullet Point Summarization of Long Financial Earnings Call Transcripts

TL;DR

This paper introduces a novel method for summarizing long financial earnings call transcripts into bullet points, using an unsupervised extractive approach and instruction-tuned abstractive models, achieving state-of-the-art results.

Contribution

It presents a new approach combining extractive and abstractive techniques for financial document summarization, specifically tailored for long earnings call transcripts.

Findings

Achieved 14.88% higher ROUGE scores than baselines.

Generated factually consistent bullet point summaries.

Demonstrated effectiveness on the ECTSum dataset.

Abstract

While automatic summarization techniques have made significant advancements, their primary focus has been on summarizing short news articles or documents that have clear structural patterns like scientific articles or government reports. There has not been much exploration into developing efficient methods for summarizing financial documents, which often contain complex facts and figures. Here, we study the problem of bullet point summarization of long Earning Call Transcripts (ECTs) using the recently released ECTSum dataset. We leverage an unsupervised question-based extractive module followed by a parameter efficient instruction-tuned abstractive module to solve this task. Our proposed model FLAN-FinBPS achieves new state-of-the-art performances outperforming the strongest baseline with 14.88% average ROUGE score gain, and is capable of generating factually consistent bullet point summaries that capture the important facts discussed in the ECTs.