@inproceedings{son-etal-2022-boosting,
title = "Boosting Code Summarization by Embedding Code Structures",
author = "Son, Jikyoeng and
Hahn, Joonghyuk and
Seo, HyeonTae and
Han, Yo-Sub",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.521",
pages = "5966--5977",
abstract = "Recent research on code summarization relies on the structural information from the abstract syntax tree (AST) of source codes. It is, however, questionable whether it is the most effective to use AST for expressing the structural information. We find that a program dependency graph (PDG) can represent the structure of a code more effectively. We propose PDG Boosting Module (PBM) that encodes PDG into graph embedding and the framework to implement the proposed PBM with the existing models. PBM achieves improvements of 6.67{\%} (BLEU) and 7.47{\%} (ROUGE) on average. We then analyze the experimental results, and examine how PBM helps the training of baseline models and its performance robustness. For the validation of robustness, we measure the performance of an out-of-domain benchmark dataset, and confirm its robustness. In addition, we apply a new evaluation measure, SBERT score, to evaluate the semantic performance. The models implemented with PBM improve the performance of SBERT score. This implies that they generate summaries that are semantically more similar to the reference summary.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="son-etal-2022-boosting">
<titleInfo>
<title>Boosting Code Summarization by Embedding Code Structures</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jikyoeng</namePart>
<namePart type="family">Son</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joonghyuk</namePart>
<namePart type="family">Hahn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">HyeonTae</namePart>
<namePart type="family">Seo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yo-Sub</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</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>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</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">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent research on code summarization relies on the structural information from the abstract syntax tree (AST) of source codes. It is, however, questionable whether it is the most effective to use AST for expressing the structural information. We find that a program dependency graph (PDG) can represent the structure of a code more effectively. We propose PDG Boosting Module (PBM) that encodes PDG into graph embedding and the framework to implement the proposed PBM with the existing models. PBM achieves improvements of 6.67% (BLEU) and 7.47% (ROUGE) on average. We then analyze the experimental results, and examine how PBM helps the training of baseline models and its performance robustness. For the validation of robustness, we measure the performance of an out-of-domain benchmark dataset, and confirm its robustness. In addition, we apply a new evaluation measure, SBERT score, to evaluate the semantic performance. The models implemented with PBM improve the performance of SBERT score. This implies that they generate summaries that are semantically more similar to the reference summary.</abstract>
<identifier type="citekey">son-etal-2022-boosting</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.521</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>5966</start>
<end>5977</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Boosting Code Summarization by Embedding Code Structures
%A Son, Jikyoeng
%A Hahn, Joonghyuk
%A Seo, HyeonTae
%A Han, Yo-Sub
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F son-etal-2022-boosting
%X Recent research on code summarization relies on the structural information from the abstract syntax tree (AST) of source codes. It is, however, questionable whether it is the most effective to use AST for expressing the structural information. We find that a program dependency graph (PDG) can represent the structure of a code more effectively. We propose PDG Boosting Module (PBM) that encodes PDG into graph embedding and the framework to implement the proposed PBM with the existing models. PBM achieves improvements of 6.67% (BLEU) and 7.47% (ROUGE) on average. We then analyze the experimental results, and examine how PBM helps the training of baseline models and its performance robustness. For the validation of robustness, we measure the performance of an out-of-domain benchmark dataset, and confirm its robustness. In addition, we apply a new evaluation measure, SBERT score, to evaluate the semantic performance. The models implemented with PBM improve the performance of SBERT score. This implies that they generate summaries that are semantically more similar to the reference summary.
%U https://aclanthology.org/2022.coling-1.521
%P 5966-5977
Markdown (Informal)
[Boosting Code Summarization by Embedding Code Structures](https://aclanthology.org/2022.coling-1.521) (Son et al., COLING 2022)
ACL
- Jikyoeng Son, Joonghyuk Hahn, HyeonTae Seo, and Yo-Sub Han. 2022. Boosting Code Summarization by Embedding Code Structures. In Proceedings of the 29th International Conference on Computational Linguistics, pages 5966–5977, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.