DSC-IITISM at FinCausal 2021: Combining POS tagging with Attention-based Contextual Representations for Identifying Causal Relationships in Financial Documents

2021/10/31 by Gunjan Haldar, Haldar, Gunjan, Aman Mittal +3
Computer Science · #Advanced Text Analysis Techniques #Sentiment Analysis and Opinion Mining #Topic Modeling #acm:68T50 #acm:91F20 #cs.AI #cs.CL #msc:68T50 #msc:91F20

paper · pdf · doi:10.48550/arxiv.2111.00490

5 pages, 5 tables

arxiv created 2021/10/31 · arxiv updated 2021/11/02

Abstract

Causality detection draws plenty of attention in the field of Natural Language Processing and linguistics research. It has essential applications in information retrieval, event prediction, question answering, financial analysis, and market research. In this study, we explore several methods to identify and extract cause-effect pairs in financial documents using transformers. For this purpose, we propose an approach that combines POS tagging with the BIO scheme, which can be integrated with modern transformer models to address this challenge of identifying causality in a given text. Our best methodology achieves an F1-Score of 0.9551, and an Exact Match Score of 0.8777 on the blind test in the FinCausal-2021 Shared Task at the FinCausal 2021 Workshop.

Related

• Financial Document Causality Detection Shared Task (FinCausal 2020)
• IIT_kgp at FinCausal 2020, Shared Task 1: Causality Detection using Sentence Embeddings in Financial Reports
• A Generative Approach for Financial Causality Extraction
• Causal BERT : Language models for causality detection between events expressed in text
• BoschAI @ Causal News Corpus 2023: Robust Cause-Effect Span Extraction using Multi-Layer Sequence Tagging and Data Augmentation