Domino at FinCausal 2020, Task 1 and 2: Causal Extraction System

Sharanya Chakravarthy, Tushar Kanakagiri, Karthik Radhakrishnan, Anjana Umapathy


Abstract
Automatic identification of cause-effect relationships from data is a challenging but important problem in artificial intelligence. Identifying semantic relationships has become increasingly important for multiple downstream applications like Question Answering, Information Retrieval and Event Prediction. In this work, we tackle the problem of causal relationship extraction from financial news using the FinCausal 2020 dataset. We tackle two tasks - 1) Detecting the presence of causal relationships and 2) Extracting segments corresponding to cause and effect from news snippets. We propose Transformer based sequence and token classification models with post-processing rules which achieve an F1 score of 96.12 and 79.60 on Tasks 1 and 2 respectively.
Anthology ID:
2020.fnp-1.15
Volume:
Proceedings of the 1st Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Venues:
COLING | FNP
SIG:
Publisher:
COLING
Note:
Pages:
90–94
Language:
URL:
https://aclanthology.org/2020.fnp-1.15
DOI:
Bibkey:
Cite (ACL):
Sharanya Chakravarthy, Tushar Kanakagiri, Karthik Radhakrishnan, and Anjana Umapathy. 2020. Domino at FinCausal 2020, Task 1 and 2: Causal Extraction System. In Proceedings of the 1st Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation, pages 90–94, Barcelona, Spain (Online). COLING.
Cite (Informal):
Domino at FinCausal 2020, Task 1 and 2: Causal Extraction System (Chakravarthy et al., FNP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.fnp-1.15.pdf
Code
 sharanyarc96/domino-fincausal2020
Data
SQuAD