Automatic Question Answering From Large ESG Reports

Pulkit Parikh and Julia Penfield
Additional contact information
Pulkit Parikh: VelocityEHS, USA
Julia Penfield: VelocityEHS, USA

International Journal of Data Warehousing and Mining (IJDWM), 2024, vol. 20, issue 1, 1-21

Abstract: ESG reports contain crucial information about the corporations' environmental impact, social responsibilities, and governance. Many compliance audits rely on answering questions based on these reports. Moreover, for tasks such as Scope 3 GHG emissions estimation, a company needs to look at the ESG reports of all its typically numerous suppliers to tabulate its own compliance reports. Manually finding specific information from these large documents is immensely time-consuming. This paper presents the first system that automatically answers questions from an ESG report, using advanced machine learning and natural language processing. The proposed system also locates and highlights a cropped screenshot from the report providing the answer. The authors devise two methods for inferring the textual answer, one based on a transformer model pre-trained for extractive question answering and another using a large language model. The task-agnostic method overcomes the challenge of the lengthiness of ESG reports in a cost-effective manner.

Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://services.igi-global.com/resolvedoi/resolve.aspx?doi=10.4018/IJDWM.352513 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:igg:jdwm00:v:20:y:2024:i:1:p:1-21

Access Statistics for this article

International Journal of Data Warehousing and Mining (IJDWM) is currently edited by Eric Pardede

More articles in International Journal of Data Warehousing and Mining (IJDWM) from IGI Global
Bibliographic data for series maintained by Journal Editor ().