Evaluating Multilingual Language Models for Cross-Lingual ESG Issue Identification

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

Abstract

The automation of information extraction from ESG reports has recently become a topic of increasing interest in the Natural Language Processing community. While such information is highly relevant for socially responsible investments, identifying the specific issues discussed in a corporate social responsibility report is one of the first steps in an information extraction pipeline. In this paper, we evaluate methods for tackling the Multilingual Environmental, Social and Governance (ESG) Issue Identification Task. Our experiments use existing datasets in English, French and Chinese with a unified label set. Leveraging multilingual language models, we compare two approaches that are commonly adopted for the given task: off-the-shelf and fine-tuning. We show that fine-tuning models end-to-end is more robust than off-the-shelf methods. Additionally, translating text into the same language has negligible performance benefits.
Original languageEnglish
Title of host publicationJoint Workshop of the 7th Financial Technology and Natural Language Processing, the 5th Knowledge Discovery from Unstructured Data in Financial Services and the 4th Economics and Natural Language Processing, FinNLP-KDF-ECONLP 2024 at LREC-COLING 2024 - Workshop Proceedings
EditorsChung-Chi Chen, Zhiqiang Ma, Udo Hahn
PublisherAssociation for Computational Linguistics (ACL)
Pages50-58
Number of pages9
ISBN (Electronic)978-2-493814-19-7
Publication statusPublished - May 2024
EventJoint Workshop of the 7th Financial Technology and Natural Language Processing (FinNLP), the 5th Knowledge Discovery from Unstructured Data in Financial Services (KDF), and The 4th Workshop on Economics and Natural Language Processing (ECONLP) - Turin, Italy
Duration: 20 May 202420 May 2024
https://sites.google.com/nlg.csie.ntu.edu.tw/finnlp-kdf-2024/call-for-papers

Publication series

NameJoint Workshop of the 7th Financial Technology and Natural Language Processing, the 5th Knowledge Discovery from Unstructured Data in Financial Services and the 4th Economics and Natural Language Processing, FinNLP-KDF-ECONLP 2024 at LREC-COLING 2024 - Workshop Proceedings

Conference

ConferenceJoint Workshop of the 7th Financial Technology and Natural Language Processing (FinNLP), the 5th Knowledge Discovery from Unstructured Data in Financial Services (KDF), and The 4th Workshop on Economics and Natural Language Processing (ECONLP)
Abbreviated titlefinnlp-kdf-2024
Country/TerritoryItaly
CityTurin
Period20/05/2420/05/24
Internet address

Keywords

  • ESG Reports
  • Pre-trained Language Models
  • Cross-lingual Transfer
  • Text Classification
  • Multilingual NLP

Fingerprint

Dive into the research topics of 'Evaluating Multilingual Language Models for Cross-Lingual ESG Issue Identification'. Together they form a unique fingerprint.

Cite this