@inproceedings{cho-etal-2023-sir,
title = "{SIR}-{ABSC}: Incorporating Syntax into {R}o{BERT}a-based Sentiment Analysis Models with a Special Aggregator Token",
author = "Cho, Ikhyun and
Jung, Yoonhwa and
Hockenmaier, Julia",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.572",
doi = "10.18653/v1/2023.findings-emnlp.572",
pages = "8535--8550",
abstract = "We present a simple, but effective method to incorporate syntactic dependency information directly into transformer-based language models (e.g. RoBERTa) for tasks such as Aspect-Based Sentiment Classification (ABSC), where the desired output depends on specific input tokens. In contrast to prior approaches to ABSC that capture syntax by combining language models with graph neural networks over dependency trees, our model, Syntax-Integrated RoBERTa for ABSC (SIR-ABSC) incorporates syntax directly into the language model by using a novel aggregator token. Yet, SIR-ABSC outperforms these more complex models, yielding new state-of-the-art results on ABSC.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cho-etal-2023-sir">
<titleInfo>
<title>SIR-ABSC: Incorporating Syntax into RoBERTa-based Sentiment Analysis Models with a Special Aggregator Token</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ikhyun</namePart>
<namePart type="family">Cho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoonhwa</namePart>
<namePart type="family">Jung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Hockenmaier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a simple, but effective method to incorporate syntactic dependency information directly into transformer-based language models (e.g. RoBERTa) for tasks such as Aspect-Based Sentiment Classification (ABSC), where the desired output depends on specific input tokens. In contrast to prior approaches to ABSC that capture syntax by combining language models with graph neural networks over dependency trees, our model, Syntax-Integrated RoBERTa for ABSC (SIR-ABSC) incorporates syntax directly into the language model by using a novel aggregator token. Yet, SIR-ABSC outperforms these more complex models, yielding new state-of-the-art results on ABSC.</abstract>
<identifier type="citekey">cho-etal-2023-sir</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.572</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.572</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>8535</start>
<end>8550</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SIR-ABSC: Incorporating Syntax into RoBERTa-based Sentiment Analysis Models with a Special Aggregator Token
%A Cho, Ikhyun
%A Jung, Yoonhwa
%A Hockenmaier, Julia
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F cho-etal-2023-sir
%X We present a simple, but effective method to incorporate syntactic dependency information directly into transformer-based language models (e.g. RoBERTa) for tasks such as Aspect-Based Sentiment Classification (ABSC), where the desired output depends on specific input tokens. In contrast to prior approaches to ABSC that capture syntax by combining language models with graph neural networks over dependency trees, our model, Syntax-Integrated RoBERTa for ABSC (SIR-ABSC) incorporates syntax directly into the language model by using a novel aggregator token. Yet, SIR-ABSC outperforms these more complex models, yielding new state-of-the-art results on ABSC.
%R 10.18653/v1/2023.findings-emnlp.572
%U https://aclanthology.org/2023.findings-emnlp.572
%U https://doi.org/10.18653/v1/2023.findings-emnlp.572
%P 8535-8550
Markdown (Informal)
[SIR-ABSC: Incorporating Syntax into RoBERTa-based Sentiment Analysis Models with a Special Aggregator Token](https://aclanthology.org/2023.findings-emnlp.572) (Cho et al., Findings 2023)
ACL