@inproceedings{goel-etal-2022-tcs,
title = "{TCS} {WITM} 2022@{F}in{S}im4-{ESG}: Augmenting {BERT} with Linguistic and Semantic features for {ESG} data classification",
author = "Goel, Tushar and
Chauhan, Vipul and
Sangwan, Suyash and
Verma, Ishan and
Dasgupta, Tirthankar and
Dey, Lipika",
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-1.32",
doi = "10.18653/v1/2022.finnlp-1.32",
pages = "235--242",
abstract = "Advanced neural network architectures have provided several opportunities to develop systems to automatically capture information from domain-specific unstructured text sources. The FinSim4-ESG shared task, collocated with the FinNLP workshop, proposed two sub-tasks. In sub-task1, the challenge was to design systems that could utilize contextual word embeddings along with sustainability resources to elaborate an ESG taxonomy. In the second sub-task, participants were asked to design a system that could classify sentences into sustainable or unsustainable sentences. In this paper, we utilize semantic similarity features along with BERT embeddings to segregate domain terms into a fixed number of class labels. The proposed model not only considers the contextual BERT embeddings but also incorporates Word2Vec, cosine, and Jaccard similarity which gives word-level importance to the model. For sentence classification, several linguistic elements along with BERT embeddings were used as classification features. We have shown a detailed ablation study for the proposed models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="goel-etal-2022-tcs">
<titleInfo>
<title>TCS WITM 2022@FinSim4-ESG: Augmenting BERT with Linguistic and Semantic features for ESG data classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tushar</namePart>
<namePart type="family">Goel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vipul</namePart>
<namePart type="family">Chauhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suyash</namePart>
<namePart type="family">Sangwan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ishan</namePart>
<namePart type="family">Verma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tirthankar</namePart>
<namePart type="family">Dasgupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lipika</namePart>
<namePart type="family">Dey</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>Advanced neural network architectures have provided several opportunities to develop systems to automatically capture information from domain-specific unstructured text sources. The FinSim4-ESG shared task, collocated with the FinNLP workshop, proposed two sub-tasks. In sub-task1, the challenge was to design systems that could utilize contextual word embeddings along with sustainability resources to elaborate an ESG taxonomy. In the second sub-task, participants were asked to design a system that could classify sentences into sustainable or unsustainable sentences. In this paper, we utilize semantic similarity features along with BERT embeddings to segregate domain terms into a fixed number of class labels. The proposed model not only considers the contextual BERT embeddings but also incorporates Word2Vec, cosine, and Jaccard similarity which gives word-level importance to the model. For sentence classification, several linguistic elements along with BERT embeddings were used as classification features. We have shown a detailed ablation study for the proposed models.</abstract>
<identifier type="citekey">goel-etal-2022-tcs</identifier>
<identifier type="doi">10.18653/v1/2022.finnlp-1.32</identifier>
<location>
<url>https://aclanthology.org/2022.finnlp-1.32</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>235</start>
<end>242</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TCS WITM 2022@FinSim4-ESG: Augmenting BERT with Linguistic and Semantic features for ESG data classification
%A Goel, Tushar
%A Chauhan, Vipul
%A Sangwan, Suyash
%A Verma, Ishan
%A Dasgupta, Tirthankar
%A Dey, Lipika
%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 goel-etal-2022-tcs
%X Advanced neural network architectures have provided several opportunities to develop systems to automatically capture information from domain-specific unstructured text sources. The FinSim4-ESG shared task, collocated with the FinNLP workshop, proposed two sub-tasks. In sub-task1, the challenge was to design systems that could utilize contextual word embeddings along with sustainability resources to elaborate an ESG taxonomy. In the second sub-task, participants were asked to design a system that could classify sentences into sustainable or unsustainable sentences. In this paper, we utilize semantic similarity features along with BERT embeddings to segregate domain terms into a fixed number of class labels. The proposed model not only considers the contextual BERT embeddings but also incorporates Word2Vec, cosine, and Jaccard similarity which gives word-level importance to the model. For sentence classification, several linguistic elements along with BERT embeddings were used as classification features. We have shown a detailed ablation study for the proposed models.
%R 10.18653/v1/2022.finnlp-1.32
%U https://aclanthology.org/2022.finnlp-1.32
%U https://doi.org/10.18653/v1/2022.finnlp-1.32
%P 235-242
Markdown (Informal)
[TCS WITM 2022@FinSim4-ESG: Augmenting BERT with Linguistic and Semantic features for ESG data classification](https://aclanthology.org/2022.finnlp-1.32) (Goel et al., FinNLP 2022)
ACL