@inproceedings{dakle-etal-2022-using,
title = "Using Transformer-based Models for Taxonomy Enrichment and Sentence Classification",
author = "Dakle, Parag Pravin and
Patil, Shrikumar and
Rallabandi, Sai Krishna and
Hegde, Chaitra and
Raghavan, Preethi",
editor = "Chen, Chung-Chi and
Huang, Hen-Hsen and
Takamura, Hiroya and
Chen, Hsin-Hsi",
booktitle = "Proceedings of the Fourth Workshop on Financial Technology and Natural Language Processing (FinNLP)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.finnlp-1.34",
doi = "10.18653/v1/2022.finnlp-1.34",
pages = "250--258",
abstract = "In this paper, we present a system that addresses the taxonomy enrichment problem for Environment, Social and Governance issues in the financial domain, as well as classifying sentences as sustainable or unsustainable, for FinSim4-ESG, a shared task for the FinNLP workshop at IJCAI-2022. We first created a derived dataset for taxonomy enrichment by using a sentence-BERT-based paraphrase detector (Reimers and Gurevych, 2019) (on the train set) to create positive and negative term-concept pairs. We then model the problem by fine-tuning the sentence-BERT-based paraphrase detector on this derived dataset, and use it as the encoder, and use a Logistic Regression classifier as the decoder, resulting in test Accuracy: 0.6 and Avg. Rank: 1.97. In case of the sentence classification task, the best-performing classifier (Accuracy: 0.92) consists of a pre-trained RoBERTa model (Liu et al., 2019a) as the encoder and a Feed Forward Neural Network classifier as the decoder.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dakle-etal-2022-using">
<titleInfo>
<title>Using Transformer-based Models for Taxonomy Enrichment and Sentence Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Parag</namePart>
<namePart type="given">Pravin</namePart>
<namePart type="family">Dakle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shrikumar</namePart>
<namePart type="family">Patil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sai</namePart>
<namePart type="given">Krishna</namePart>
<namePart type="family">Rallabandi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chaitra</namePart>
<namePart type="family">Hegde</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preethi</namePart>
<namePart type="family">Raghavan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on Financial Technology and Natural Language Processing (FinNLP)</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we present a system that addresses the taxonomy enrichment problem for Environment, Social and Governance issues in the financial domain, as well as classifying sentences as sustainable or unsustainable, for FinSim4-ESG, a shared task for the FinNLP workshop at IJCAI-2022. We first created a derived dataset for taxonomy enrichment by using a sentence-BERT-based paraphrase detector (Reimers and Gurevych, 2019) (on the train set) to create positive and negative term-concept pairs. We then model the problem by fine-tuning the sentence-BERT-based paraphrase detector on this derived dataset, and use it as the encoder, and use a Logistic Regression classifier as the decoder, resulting in test Accuracy: 0.6 and Avg. Rank: 1.97. In case of the sentence classification task, the best-performing classifier (Accuracy: 0.92) consists of a pre-trained RoBERTa model (Liu et al., 2019a) as the encoder and a Feed Forward Neural Network classifier as the decoder.</abstract>
<identifier type="citekey">dakle-etal-2022-using</identifier>
<identifier type="doi">10.18653/v1/2022.finnlp-1.34</identifier>
<location>
<url>https://aclanthology.org/2022.finnlp-1.34</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>250</start>
<end>258</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Using Transformer-based Models for Taxonomy Enrichment and Sentence Classification
%A Dakle, Parag Pravin
%A Patil, Shrikumar
%A Rallabandi, Sai Krishna
%A Hegde, Chaitra
%A Raghavan, Preethi
%Y Chen, Chung-Chi
%Y Huang, Hen-Hsen
%Y Takamura, Hiroya
%Y Chen, Hsin-Hsi
%S Proceedings of the Fourth Workshop on Financial Technology and Natural Language Processing (FinNLP)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F dakle-etal-2022-using
%X In this paper, we present a system that addresses the taxonomy enrichment problem for Environment, Social and Governance issues in the financial domain, as well as classifying sentences as sustainable or unsustainable, for FinSim4-ESG, a shared task for the FinNLP workshop at IJCAI-2022. We first created a derived dataset for taxonomy enrichment by using a sentence-BERT-based paraphrase detector (Reimers and Gurevych, 2019) (on the train set) to create positive and negative term-concept pairs. We then model the problem by fine-tuning the sentence-BERT-based paraphrase detector on this derived dataset, and use it as the encoder, and use a Logistic Regression classifier as the decoder, resulting in test Accuracy: 0.6 and Avg. Rank: 1.97. In case of the sentence classification task, the best-performing classifier (Accuracy: 0.92) consists of a pre-trained RoBERTa model (Liu et al., 2019a) as the encoder and a Feed Forward Neural Network classifier as the decoder.
%R 10.18653/v1/2022.finnlp-1.34
%U https://aclanthology.org/2022.finnlp-1.34
%U https://doi.org/10.18653/v1/2022.finnlp-1.34
%P 250-258
Markdown (Informal)
[Using Transformer-based Models for Taxonomy Enrichment and Sentence Classification](https://aclanthology.org/2022.finnlp-1.34) (Dakle et al., FinNLP 2022)
ACL