Fine-Tuning Language Models for Predicting the Impact of Events Associated to Financial News Articles

EasyChair Preprint 12756

Abstract

Investors and other stakeholders like consumers and employees, increasingly consider ESG factors when making decisions about investments or engaging with companies. Taking into account the importance of ESG today, FinNLP-KDF introduced the ML-ESG-3 shared task, which seeks to determine the duration of the impact of financial news articles in four languages- English, French, Korean, and Japanese. This paper describes our team, LIPI’s approach towards solving the above-mentioned task. Our final systems consist of translation, paraphrasing and f ine-tuning language models like BERT, Fin-BERT and RoBERTa for classification. We ranked first in the impact duration prediction subtask for French language.

Keyphrases: ESG, ESG impact prediction, Financial Natural Language Processing, Impact Prediction, language models

@booklet{EasyChair:12756,
  author    = {Neelabha Banerjee and Anubhav Sarkar and Swagata Chakraborty and Sohom Ghosh and Sudip Kumar Naskar},
  title     = {Fine-Tuning Language Models for Predicting the Impact of Events Associated to Financial News Articles},
  howpublished = {EasyChair Preprint 12756},
  year      = {EasyChair, 2024}}