Co-Trained Retriever-Generator Framework for Question Generation in Earnings Calls

TL;DR

This paper introduces a novel framework for generating multiple relevant questions in earnings calls, combining retrieval and generation techniques to improve question quality and relevance in professional settings.

Contribution

It presents a new multi-question generation task tailored for earnings calls and a co-trained retriever-generator model that enhances question relevance and diversity.

Findings

Outperforms existing methods in accuracy and relevance

Achieves lower perplexity in generated questions

Demonstrates effectiveness in professional earnings call contexts

Abstract

In diverse professional environments, ranging from academic conferences to corporate earnings calls, the ability to anticipate audience questions stands paramount. Traditional methods, which rely on manual assessment of an audience's background, interests, and subject knowledge, often fall short - particularly when facing large or heterogeneous groups, leading to imprecision and inefficiency. While NLP has made strides in text-based question generation, its primary focus remains on academic settings, leaving the intricate challenges of professional domains, especially earnings call conferences, underserved. Addressing this gap, our paper pioneers the multi-question generation (MQG) task specifically designed for earnings call contexts. Our methodology involves an exhaustive collection of earnings call transcripts and a novel annotation technique to classify potential questions. Furthermore, we introduce a retriever-enhanced strategy to extract relevant information. With a core aim of generating a spectrum of potential questions that analysts might pose, we derive these directly from earnings call content. Empirical evaluations underscore our approach's edge, revealing notable excellence in the accuracy, consistency, and perplexity of the questions generated.