@inproceedings{vaishampayan-etal-2023-audit,
title = "Audit Report Coverage Assessment using Sentence Classification",
author = "Vaishampayan, Sushodhan and
Ramrakhiyani, Nitin and
Pawar, Sachin and
Pawde, Aditi and
Apte, Manoj and
Palshikar, Girish",
editor = "Chen, Chung-Chi and
Huang, Hen-Hsen and
Takamura, Hiroya and
Chen, Hsin-Hsi and
Sakaji, Hiroki and
Izumi, Kiyoshi",
booktitle = "Proceedings of the Sixth Workshop on Financial Technology and Natural Language Processing",
month = nov,
year = "2023",
address = "Bali, Indonesia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.finnlp-2.4",
doi = "10.18653/v1/2023.finnlp-2.4",
pages = "31--41",
abstract = "Audit reports are a window to the financial health of a company and hence gauging coverage of various audit aspects in them is important. In this paper, we aim at determining an audit report{'}s coverage through classification of its sentences into multiple domain specific classes. In a weakly supervised setting, we employ a rule-based approach to automatically create training data for a BERT-based multi-label classifier. We then devise an ensemble to combine both the rule based and classifier approaches. Further, we employ two novel ways to improve the ensemble{'}s generalization: (i) through an active learning based approach and, (ii) through a LLM based review. We demonstrate that our proposed approaches outperform several baselines. We show utility of the proposed approaches to measure audit coverage on a large dataset of 2.8K audit reports.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vaishampayan-etal-2023-audit">
<titleInfo>
<title>Audit Report Coverage Assessment using Sentence Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sushodhan</namePart>
<namePart type="family">Vaishampayan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nitin</namePart>
<namePart type="family">Ramrakhiyani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sachin</namePart>
<namePart type="family">Pawar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aditi</namePart>
<namePart type="family">Pawde</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manoj</namePart>
<namePart type="family">Apte</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Girish</namePart>
<namePart type="family">Palshikar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Workshop on Financial Technology and Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chung-Chi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hen-Hsen</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroya</namePart>
<namePart type="family">Takamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroki</namePart>
<namePart type="family">Sakaji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kiyoshi</namePart>
<namePart type="family">Izumi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bali, Indonesia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Audit reports are a window to the financial health of a company and hence gauging coverage of various audit aspects in them is important. In this paper, we aim at determining an audit report’s coverage through classification of its sentences into multiple domain specific classes. In a weakly supervised setting, we employ a rule-based approach to automatically create training data for a BERT-based multi-label classifier. We then devise an ensemble to combine both the rule based and classifier approaches. Further, we employ two novel ways to improve the ensemble’s generalization: (i) through an active learning based approach and, (ii) through a LLM based review. We demonstrate that our proposed approaches outperform several baselines. We show utility of the proposed approaches to measure audit coverage on a large dataset of 2.8K audit reports.</abstract>
<identifier type="citekey">vaishampayan-etal-2023-audit</identifier>
<identifier type="doi">10.18653/v1/2023.finnlp-2.4</identifier>
<location>
<url>https://aclanthology.org/2023.finnlp-2.4</url>
</location>
<part>
<date>2023-11</date>
<extent unit="page">
<start>31</start>
<end>41</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Audit Report Coverage Assessment using Sentence Classification
%A Vaishampayan, Sushodhan
%A Ramrakhiyani, Nitin
%A Pawar, Sachin
%A Pawde, Aditi
%A Apte, Manoj
%A Palshikar, Girish
%Y Chen, Chung-Chi
%Y Huang, Hen-Hsen
%Y Takamura, Hiroya
%Y Chen, Hsin-Hsi
%Y Sakaji, Hiroki
%Y Izumi, Kiyoshi
%S Proceedings of the Sixth Workshop on Financial Technology and Natural Language Processing
%D 2023
%8 November
%I Association for Computational Linguistics
%C Bali, Indonesia
%F vaishampayan-etal-2023-audit
%X Audit reports are a window to the financial health of a company and hence gauging coverage of various audit aspects in them is important. In this paper, we aim at determining an audit report’s coverage through classification of its sentences into multiple domain specific classes. In a weakly supervised setting, we employ a rule-based approach to automatically create training data for a BERT-based multi-label classifier. We then devise an ensemble to combine both the rule based and classifier approaches. Further, we employ two novel ways to improve the ensemble’s generalization: (i) through an active learning based approach and, (ii) through a LLM based review. We demonstrate that our proposed approaches outperform several baselines. We show utility of the proposed approaches to measure audit coverage on a large dataset of 2.8K audit reports.
%R 10.18653/v1/2023.finnlp-2.4
%U https://aclanthology.org/2023.finnlp-2.4
%U https://doi.org/10.18653/v1/2023.finnlp-2.4
%P 31-41
Markdown (Informal)
[Audit Report Coverage Assessment using Sentence Classification](https://aclanthology.org/2023.finnlp-2.4) (Vaishampayan et al., FinNLP-WS 2023)
ACL
- Sushodhan Vaishampayan, Nitin Ramrakhiyani, Sachin Pawar, Aditi Pawde, Manoj Apte, and Girish Palshikar. 2023. Audit Report Coverage Assessment using Sentence Classification. In Proceedings of the Sixth Workshop on Financial Technology and Natural Language Processing, pages 31–41, Bali, Indonesia. Association for Computational Linguistics.