Sequence-to-Sequence Learning-Based Conversion of Pseudo-Code to Source Code Using Neural Translation Approach
Pseudo-code refers to an informal means of representing algorithms that do not require the exact syntax of a computer programming language. Pseudo-code helps developers and researchers represent their algorithms using human-readable language. Generally, researchers can convert the pseudo-code into c...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9723496/ |
| _version_ | 1818996271275311104 |
|---|---|
| author | Uzzal Kumar Acharjee Minhazul Arefin Kazi Mojammel Hossen Mohammed Nasir Uddin Md. Ashraf Uddin Linta Islam |
| author_facet | Uzzal Kumar Acharjee Minhazul Arefin Kazi Mojammel Hossen Mohammed Nasir Uddin Md. Ashraf Uddin Linta Islam |
| author_sort | Uzzal Kumar Acharjee |
| collection | DOAJ |
| description | Pseudo-code refers to an informal means of representing algorithms that do not require the exact syntax of a computer programming language. Pseudo-code helps developers and researchers represent their algorithms using human-readable language. Generally, researchers can convert the pseudo-code into computer source code using different conversion techniques. The efficiency of such conversion methods is measured based on the converted algorithm’s correctness. Researchers have already explored diverse technologies to devise conversion methods with higher accuracy. This paper proposes a novel pseudo-code conversion learning method that includes natural language processing-based text preprocessing and a sequence-to-sequence deep learning-based model trained with the SPoC dataset. We conducted an extensive experiment on our designed algorithm using descriptive bilingual understudy scoring and compared our results with state-of-the-art techniques. Result analysis shows that our approach is more accurate and efficient than other existing conversion methods in terms of several performances metrics. Furthermore, the proposed method outperforms the existing approaches because our method utilizes two Long-Short-Term-Memory networks that might increase the accuracy. |
| first_indexed | 2024-12-20T21:27:05Z |
| format | Article |
| id | doaj.art-5bb1939b7a1e41a0981f1f102f7053de |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-20T21:27:05Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-5bb1939b7a1e41a0981f1f102f7053de2022-12-21T19:26:08ZengIEEEIEEE Access2169-35362022-01-0110267302674210.1109/ACCESS.2022.31555589723496Sequence-to-Sequence Learning-Based Conversion of Pseudo-Code to Source Code Using Neural Translation ApproachUzzal Kumar Acharjee0Minhazul Arefin1https://orcid.org/0000-0003-4330-8745Kazi Mojammel Hossen2https://orcid.org/0000-0002-5342-454XMohammed Nasir Uddin3Md. Ashraf Uddin4https://orcid.org/0000-0002-4316-4975Linta Islam5Department of Computer Science & Engineering, Jagannath University, Dhaka, BangladeshDepartment of Computer Science & Engineering, Jagannath University, Dhaka, BangladeshDepartment of Computer Science & Engineering, Jagannath University, Dhaka, BangladeshDepartment of Computer Science & Engineering, Jagannath University, Dhaka, BangladeshInternet Commerce Security Laboratory, Centre for Informatics and Applied Optimisation, Federation University, Ballarat, VIC, AustraliaDepartment of Computer Science & Engineering, Jagannath University, Dhaka, BangladeshPseudo-code refers to an informal means of representing algorithms that do not require the exact syntax of a computer programming language. Pseudo-code helps developers and researchers represent their algorithms using human-readable language. Generally, researchers can convert the pseudo-code into computer source code using different conversion techniques. The efficiency of such conversion methods is measured based on the converted algorithm’s correctness. Researchers have already explored diverse technologies to devise conversion methods with higher accuracy. This paper proposes a novel pseudo-code conversion learning method that includes natural language processing-based text preprocessing and a sequence-to-sequence deep learning-based model trained with the SPoC dataset. We conducted an extensive experiment on our designed algorithm using descriptive bilingual understudy scoring and compared our results with state-of-the-art techniques. Result analysis shows that our approach is more accurate and efficient than other existing conversion methods in terms of several performances metrics. Furthermore, the proposed method outperforms the existing approaches because our method utilizes two Long-Short-Term-Memory networks that might increase the accuracy.https://ieeexplore.ieee.org/document/9723496/Sequence-to-sequence learning modelnatural language processingpseudo-codemachine translationsource code |
| spellingShingle | Uzzal Kumar Acharjee Minhazul Arefin Kazi Mojammel Hossen Mohammed Nasir Uddin Md. Ashraf Uddin Linta Islam Sequence-to-Sequence Learning-Based Conversion of Pseudo-Code to Source Code Using Neural Translation Approach IEEE Access Sequence-to-sequence learning model natural language processing pseudo-code machine translation source code |
| title | Sequence-to-Sequence Learning-Based Conversion of Pseudo-Code to Source Code Using Neural Translation Approach |
| title_full | Sequence-to-Sequence Learning-Based Conversion of Pseudo-Code to Source Code Using Neural Translation Approach |
| title_fullStr | Sequence-to-Sequence Learning-Based Conversion of Pseudo-Code to Source Code Using Neural Translation Approach |
| title_full_unstemmed | Sequence-to-Sequence Learning-Based Conversion of Pseudo-Code to Source Code Using Neural Translation Approach |
| title_short | Sequence-to-Sequence Learning-Based Conversion of Pseudo-Code to Source Code Using Neural Translation Approach |
| title_sort | sequence to sequence learning based conversion of pseudo code to source code using neural translation approach |
| topic | Sequence-to-sequence learning model natural language processing pseudo-code machine translation source code |
| url | https://ieeexplore.ieee.org/document/9723496/ |
| work_keys_str_mv | AT uzzalkumaracharjee sequencetosequencelearningbasedconversionofpseudocodetosourcecodeusingneuraltranslationapproach AT minhazularefin sequencetosequencelearningbasedconversionofpseudocodetosourcecodeusingneuraltranslationapproach AT kazimojammelhossen sequencetosequencelearningbasedconversionofpseudocodetosourcecodeusingneuraltranslationapproach AT mohammednasiruddin sequencetosequencelearningbasedconversionofpseudocodetosourcecodeusingneuraltranslationapproach AT mdashrafuddin sequencetosequencelearningbasedconversionofpseudocodetosourcecodeusingneuraltranslationapproach AT lintaislam sequencetosequencelearningbasedconversionofpseudocodetosourcecodeusingneuraltranslationapproach |