@inproceedings{choi-etal-2022-scene,
title = "Scene Graph Parsing via {A}bstract {M}eaning {R}epresentation in Pre-trained Language Models",
author = "Choi, Woo Suk and
Heo, Yu-Jung and
Punithan, Dharani and
Zhang, Byoung-Tak",
editor = "Wu, Lingfei and
Liu, Bang and
Mihalcea, Rada and
Pei, Jian and
Zhang, Yue and
Li, Yunyao",
booktitle = "Proceedings of the 2nd Workshop on Deep Learning on Graphs for Natural Language Processing (DLG4NLP 2022)",
month = jul,
year = "2022",
address = "Seattle, Washington",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.dlg4nlp-1.4",
doi = "10.18653/v1/2022.dlg4nlp-1.4",
pages = "30--35",
abstract = "In this work, we propose the application of abstract meaning representation (AMR) based semantic parsing models to parse textual descriptions of a visual scene into scene graphs, which is the first work to the best of our knowledge. Previous works examined scene graph parsing from textual descriptions using dependency parsing and left the AMR parsing approach as future work since sophisticated methods are required to apply AMR. Hence, we use pre-trained AMR parsing models to parse the region descriptions of visual scenes (i.e. images) into AMR graphs and pre-trained language models (PLM), BART and T5, to parse AMR graphs into scene graphs. The experimental results show that our approach explicitly captures high-level semantics from textual descriptions of visual scenes, such as objects, attributes of objects, and relationships between objects. Our textual scene graph parsing approach outperforms the previous state-of-the-art results by 9.3{\%} in the SPICE metric score.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="choi-etal-2022-scene">
<titleInfo>
<title>Scene Graph Parsing via Abstract Meaning Representation in Pre-trained Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Woo</namePart>
<namePart type="given">Suk</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu-Jung</namePart>
<namePart type="family">Heo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dharani</namePart>
<namePart type="family">Punithan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Byoung-Tak</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Deep Learning on Graphs for Natural Language Processing (DLG4NLP 2022)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lingfei</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rada</namePart>
<namePart type="family">Mihalcea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jian</namePart>
<namePart type="family">Pei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, Washington</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this work, we propose the application of abstract meaning representation (AMR) based semantic parsing models to parse textual descriptions of a visual scene into scene graphs, which is the first work to the best of our knowledge. Previous works examined scene graph parsing from textual descriptions using dependency parsing and left the AMR parsing approach as future work since sophisticated methods are required to apply AMR. Hence, we use pre-trained AMR parsing models to parse the region descriptions of visual scenes (i.e. images) into AMR graphs and pre-trained language models (PLM), BART and T5, to parse AMR graphs into scene graphs. The experimental results show that our approach explicitly captures high-level semantics from textual descriptions of visual scenes, such as objects, attributes of objects, and relationships between objects. Our textual scene graph parsing approach outperforms the previous state-of-the-art results by 9.3% in the SPICE metric score.</abstract>
<identifier type="citekey">choi-etal-2022-scene</identifier>
<identifier type="doi">10.18653/v1/2022.dlg4nlp-1.4</identifier>
<location>
<url>https://aclanthology.org/2022.dlg4nlp-1.4</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>30</start>
<end>35</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Scene Graph Parsing via Abstract Meaning Representation in Pre-trained Language Models
%A Choi, Woo Suk
%A Heo, Yu-Jung
%A Punithan, Dharani
%A Zhang, Byoung-Tak
%Y Wu, Lingfei
%Y Liu, Bang
%Y Mihalcea, Rada
%Y Pei, Jian
%Y Zhang, Yue
%Y Li, Yunyao
%S Proceedings of the 2nd Workshop on Deep Learning on Graphs for Natural Language Processing (DLG4NLP 2022)
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, Washington
%F choi-etal-2022-scene
%X In this work, we propose the application of abstract meaning representation (AMR) based semantic parsing models to parse textual descriptions of a visual scene into scene graphs, which is the first work to the best of our knowledge. Previous works examined scene graph parsing from textual descriptions using dependency parsing and left the AMR parsing approach as future work since sophisticated methods are required to apply AMR. Hence, we use pre-trained AMR parsing models to parse the region descriptions of visual scenes (i.e. images) into AMR graphs and pre-trained language models (PLM), BART and T5, to parse AMR graphs into scene graphs. The experimental results show that our approach explicitly captures high-level semantics from textual descriptions of visual scenes, such as objects, attributes of objects, and relationships between objects. Our textual scene graph parsing approach outperforms the previous state-of-the-art results by 9.3% in the SPICE metric score.
%R 10.18653/v1/2022.dlg4nlp-1.4
%U https://aclanthology.org/2022.dlg4nlp-1.4
%U https://doi.org/10.18653/v1/2022.dlg4nlp-1.4
%P 30-35
Markdown (Informal)
[Scene Graph Parsing via Abstract Meaning Representation in Pre-trained Language Models](https://aclanthology.org/2022.dlg4nlp-1.4) (Choi et al., DLG4NLP 2022)
ACL