@inproceedings{bhushan-lee-2022-block,
title = "Block Diagram-to-Text: Understanding Block Diagram Images by Generating Natural Language Descriptors",
author = "Bhushan, Shreyanshu and
Lee, Minho",
editor = "He, Yulan and
Ji, Heng and
Li, Sujian and
Liu, Yang and
Chang, Chua-Hui",
booktitle = "Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022",
month = nov,
year = "2022",
address = "Online only",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-aacl.15",
pages = "153--168",
abstract = "Block diagrams are very popular for representing a workflow or process of a model. Understanding block diagrams by generating summaries can be extremely useful in document summarization. It can also assist people in inferring key insights from block diagrams without requiring a lot of perceptual and cognitive effort. In this paper, we propose a novel task of converting block diagram images into text by presenting a framework called {``}BloSum{''}. This framework extracts the contextual meaning from the images in the form of triplets that help the language model in summary generation. We also introduce a new dataset for complex computerized block diagrams, explain the dataset preparation process, and later analyze it. Additionally, to showcase the generalization of the model, we test our method with publicly available handwritten block diagram datasets. Our evaluation with different metrics demonstrates the effectiveness of our approach that outperforms other methods and techniques.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bhushan-lee-2022-block">
<titleInfo>
<title>Block Diagram-to-Text: Understanding Block Diagram Images by Generating Natural Language Descriptors</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shreyanshu</namePart>
<namePart type="family">Bhushan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minho</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sujian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chua-Hui</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online only</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Block diagrams are very popular for representing a workflow or process of a model. Understanding block diagrams by generating summaries can be extremely useful in document summarization. It can also assist people in inferring key insights from block diagrams without requiring a lot of perceptual and cognitive effort. In this paper, we propose a novel task of converting block diagram images into text by presenting a framework called “BloSum”. This framework extracts the contextual meaning from the images in the form of triplets that help the language model in summary generation. We also introduce a new dataset for complex computerized block diagrams, explain the dataset preparation process, and later analyze it. Additionally, to showcase the generalization of the model, we test our method with publicly available handwritten block diagram datasets. Our evaluation with different metrics demonstrates the effectiveness of our approach that outperforms other methods and techniques.</abstract>
<identifier type="citekey">bhushan-lee-2022-block</identifier>
<location>
<url>https://aclanthology.org/2022.findings-aacl.15</url>
</location>
<part>
<date>2022-11</date>
<extent unit="page">
<start>153</start>
<end>168</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Block Diagram-to-Text: Understanding Block Diagram Images by Generating Natural Language Descriptors
%A Bhushan, Shreyanshu
%A Lee, Minho
%Y He, Yulan
%Y Ji, Heng
%Y Li, Sujian
%Y Liu, Yang
%Y Chang, Chua-Hui
%S Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022
%D 2022
%8 November
%I Association for Computational Linguistics
%C Online only
%F bhushan-lee-2022-block
%X Block diagrams are very popular for representing a workflow or process of a model. Understanding block diagrams by generating summaries can be extremely useful in document summarization. It can also assist people in inferring key insights from block diagrams without requiring a lot of perceptual and cognitive effort. In this paper, we propose a novel task of converting block diagram images into text by presenting a framework called “BloSum”. This framework extracts the contextual meaning from the images in the form of triplets that help the language model in summary generation. We also introduce a new dataset for complex computerized block diagrams, explain the dataset preparation process, and later analyze it. Additionally, to showcase the generalization of the model, we test our method with publicly available handwritten block diagram datasets. Our evaluation with different metrics demonstrates the effectiveness of our approach that outperforms other methods and techniques.
%U https://aclanthology.org/2022.findings-aacl.15
%P 153-168
Markdown (Informal)
[Block Diagram-to-Text: Understanding Block Diagram Images by Generating Natural Language Descriptors](https://aclanthology.org/2022.findings-aacl.15) (Bhushan & Lee, Findings 2022)
ACL