@inproceedings{kovalchuk-etal-2022-human,
title = "Human perceiving behavior modeling in evaluation of code generation models",
author = "Kovalchuk, Sergey V. and
Lomshakov, Vadim and
Aliev, Artem",
editor = "Bosselut, Antoine and
Chandu, Khyathi and
Dhole, Kaustubh and
Gangal, Varun and
Gehrmann, Sebastian and
Jernite, Yacine and
Novikova, Jekaterina and
Perez-Beltrachini, Laura",
booktitle = "Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.gem-1.24",
doi = "10.18653/v1/2022.gem-1.24",
pages = "287--294",
abstract = "Within this study, we evaluated a series of code generation models based on CodeGen and GPTNeo to compare the metric-based performance and human evaluation. For a deeper analysis of human perceiving within the evaluation procedure we{'}ve implemented a 5-level Likert scale assessment of the model output using a perceiving model based on the Theory of Planned Behavior (TPB). Through such analysis, we showed an extension of model assessment as well as a deeper understanding of the quality and applicability of generated code for practical question answering. The approach was evaluated with several model settings in order to assess diversity in quality and style of answer. With the TPB-based model, we showed a different level of perceiving the model result, namely personal understanding, agreement level, and readiness to use the particular code. With such analysis, we investigate a series of issues in code generation as natural language generation (NLG) problems observed in a practical context of programming question-answering with code.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kovalchuk-etal-2022-human">
<titleInfo>
<title>Human perceiving behavior modeling in evaluation of code generation models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sergey</namePart>
<namePart type="given">V</namePart>
<namePart type="family">Kovalchuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vadim</namePart>
<namePart type="family">Lomshakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Artem</namePart>
<namePart type="family">Aliev</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 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Antoine</namePart>
<namePart type="family">Bosselut</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khyathi</namePart>
<namePart type="family">Chandu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaustubh</namePart>
<namePart type="family">Dhole</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Varun</namePart>
<namePart type="family">Gangal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Gehrmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yacine</namePart>
<namePart type="family">Jernite</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jekaterina</namePart>
<namePart type="family">Novikova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Perez-Beltrachini</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>Within this study, we evaluated a series of code generation models based on CodeGen and GPTNeo to compare the metric-based performance and human evaluation. For a deeper analysis of human perceiving within the evaluation procedure we’ve implemented a 5-level Likert scale assessment of the model output using a perceiving model based on the Theory of Planned Behavior (TPB). Through such analysis, we showed an extension of model assessment as well as a deeper understanding of the quality and applicability of generated code for practical question answering. The approach was evaluated with several model settings in order to assess diversity in quality and style of answer. With the TPB-based model, we showed a different level of perceiving the model result, namely personal understanding, agreement level, and readiness to use the particular code. With such analysis, we investigate a series of issues in code generation as natural language generation (NLG) problems observed in a practical context of programming question-answering with code.</abstract>
<identifier type="citekey">kovalchuk-etal-2022-human</identifier>
<identifier type="doi">10.18653/v1/2022.gem-1.24</identifier>
<location>
<url>https://aclanthology.org/2022.gem-1.24</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>287</start>
<end>294</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Human perceiving behavior modeling in evaluation of code generation models
%A Kovalchuk, Sergey V.
%A Lomshakov, Vadim
%A Aliev, Artem
%Y Bosselut, Antoine
%Y Chandu, Khyathi
%Y Dhole, Kaustubh
%Y Gangal, Varun
%Y Gehrmann, Sebastian
%Y Jernite, Yacine
%Y Novikova, Jekaterina
%Y Perez-Beltrachini, Laura
%S Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F kovalchuk-etal-2022-human
%X Within this study, we evaluated a series of code generation models based on CodeGen and GPTNeo to compare the metric-based performance and human evaluation. For a deeper analysis of human perceiving within the evaluation procedure we’ve implemented a 5-level Likert scale assessment of the model output using a perceiving model based on the Theory of Planned Behavior (TPB). Through such analysis, we showed an extension of model assessment as well as a deeper understanding of the quality and applicability of generated code for practical question answering. The approach was evaluated with several model settings in order to assess diversity in quality and style of answer. With the TPB-based model, we showed a different level of perceiving the model result, namely personal understanding, agreement level, and readiness to use the particular code. With such analysis, we investigate a series of issues in code generation as natural language generation (NLG) problems observed in a practical context of programming question-answering with code.
%R 10.18653/v1/2022.gem-1.24
%U https://aclanthology.org/2022.gem-1.24
%U https://doi.org/10.18653/v1/2022.gem-1.24
%P 287-294
Markdown (Informal)
[Human perceiving behavior modeling in evaluation of code generation models](https://aclanthology.org/2022.gem-1.24) (Kovalchuk et al., GEM 2022)
ACL