@inproceedings{gupta-2020-finlp,
title = "{F}i{NLP} at {F}in{C}ausal 2020 Task 1: Mixture of {BERT}s for Causal Sentence Identification in Financial Texts",
author = "Gupta, Sarthak",
booktitle = "Proceedings of the 1st Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "COLING",
url = "https://aclanthology.org/2020.fnp-1.12",
pages = "74--79",
abstract = "This paper describes our system developed for the sub-task 1 of the FinCausal shared task in the FNP-FNS workshop held in conjunction with COLING-2020. The system classifies whether a financial news text segment contains causality or not. To address this task, we fine-tune and ensemble the generic and domain-specific BERT language models pre-trained on financial text corpora. The task data is highly imbalanced with the majority non-causal class; therefore, we train the models using strategies such as under-sampling, cost-sensitive learning, and data augmentation. Our best system achieves a weighted F1-score of 96.98 securing 4th position on the evaluation leaderboard. The code is available at https://github.com/sarthakTUM/fincausal",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gupta-2020-finlp">
<titleInfo>
<title>FiNLP at FinCausal 2020 Task 1: Mixture of BERTs for Causal Sentence Identification in Financial Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sarthak</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-dec</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation</title>
</titleInfo>
<originInfo>
<publisher>COLING</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes our system developed for the sub-task 1 of the FinCausal shared task in the FNP-FNS workshop held in conjunction with COLING-2020. The system classifies whether a financial news text segment contains causality or not. To address this task, we fine-tune and ensemble the generic and domain-specific BERT language models pre-trained on financial text corpora. The task data is highly imbalanced with the majority non-causal class; therefore, we train the models using strategies such as under-sampling, cost-sensitive learning, and data augmentation. Our best system achieves a weighted F1-score of 96.98 securing 4th position on the evaluation leaderboard. The code is available at https://github.com/sarthakTUM/fincausal</abstract>
<identifier type="citekey">gupta-2020-finlp</identifier>
<location>
<url>https://aclanthology.org/2020.fnp-1.12</url>
</location>
<part>
<date>2020-dec</date>
<extent unit="page">
<start>74</start>
<end>79</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FiNLP at FinCausal 2020 Task 1: Mixture of BERTs for Causal Sentence Identification in Financial Texts
%A Gupta, Sarthak
%S Proceedings of the 1st Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation
%D 2020
%8 dec
%I COLING
%C Barcelona, Spain (Online)
%F gupta-2020-finlp
%X This paper describes our system developed for the sub-task 1 of the FinCausal shared task in the FNP-FNS workshop held in conjunction with COLING-2020. The system classifies whether a financial news text segment contains causality or not. To address this task, we fine-tune and ensemble the generic and domain-specific BERT language models pre-trained on financial text corpora. The task data is highly imbalanced with the majority non-causal class; therefore, we train the models using strategies such as under-sampling, cost-sensitive learning, and data augmentation. Our best system achieves a weighted F1-score of 96.98 securing 4th position on the evaluation leaderboard. The code is available at https://github.com/sarthakTUM/fincausal
%U https://aclanthology.org/2020.fnp-1.12
%P 74-79
Markdown (Informal)
[FiNLP at FinCausal 2020 Task 1: Mixture of BERTs for Causal Sentence Identification in Financial Texts](https://aclanthology.org/2020.fnp-1.12) (Gupta, FNP 2020)
ACL