Zobrazeno 1 - 10
of 13
pro vyhledávání: '"Zeqi Lin"'
Publikováno v:
大数据, Vol 7, Pp 2021002-1 (2021)
With the increasing of software scale and software evolution, it is more and more important to construct software project knowledge graph for software maintenance and software development. Automatically constructing software knowledge graph with comp
Externí odkaz:
https://doaj.org/article/239b5925e35b4d869e0feff9ad14f055
Autor:
Daoguang Zan, Bei Chen, Dejian Yang, Zeqi Lin, Minsu Kim, Bei Guan, Yongji Wang, Weizhu Chen, Jian-Guang Lou
Code generation is a longstanding challenge, aiming to generate a code snippet based on a natural language description. Usually, expensive text-code paired data is essential for training a code generation model. Recently, thanks to the success of pre
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4f1980323bd4c68edb1fb6fcf3290e4d
http://arxiv.org/abs/2206.06888
http://arxiv.org/abs/2206.06888
Publikováno v:
Proceedings of the 44th International Conference on Software Engineering.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f7c727c898905598d87ea32e80f3da0b
https://doi.org/10.1145/3510003.3510118
https://doi.org/10.1145/3510003.3510118
Publikováno v:
2021 36th IEEE/ACM International Conference on Automated Software Engineering (ASE).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::23ac6a3e8925677c2b45dc3d166ae4ec
https://doi.org/10.1109/ase51524.2021.9678907
https://doi.org/10.1109/ase51524.2021.9678907
Autor:
Dongmei Zhang, Nanning Zheng, Bei Chen, Chenyao Liu, Lijie Wen, Zeqi Lin, Jian-Guang Lou, Shengnan An, Qian Liu
Publikováno v:
ACL/IJCNLP (Findings)
Neural sequence models exhibit limited compositional generalization ability in semantic parsing tasks. Compositional generalization requires algebraic recombination, i.e., dynamically recombining structured expressions in a recursive manner. However,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2378fca4646c04a9490a50c1bafb4c88
http://arxiv.org/abs/2107.06516
http://arxiv.org/abs/2107.06516
Publikováno v:
Journal of Computer Science and Technology. 34:993-1006
Searching application programming interfaces (APIs) is very important for developers to reuse software projects. Existing natural language based API search mainly faces the following challenges. 1) More accurate results are required as software proje
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0d568b5f80480ecb9564d4ab870dd0fc
https://doi.org/10.1007/s11390-019-1956-2
https://doi.org/10.1007/s11390-019-1956-2
Publikováno v:
ICPC
Searching code in a large-scale codebase using natural language queries is a common practice during software development. Deep learning-based code search methods demonstrate superior performance if models are trained with large amount of text-code pa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b8c4f35eac5d01257c45201b3a90deb1
https://doi.org/10.1145/3387904.3389278
https://doi.org/10.1145/3387904.3389278
Publikováno v:
Journal of Computer Science and Technology. 32:242-249
Software intelligent development has become one of the most important research trends in software engineering. In this paper, we put forward two key concepts — intelligent development environment (IntelliDE) and software knowledge graph — for the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3524a5e67a3e80e7ee9cac3f7d747be5
https://doi.org/10.1007/s11390-017-1718-y
https://doi.org/10.1007/s11390-017-1718-y
Publikováno v:
ASE
Code review is an important mechanism for code quality assurance both in open source software and industrial software. Reviewers usually suffer from numerous, tangled and loosely related code changes that are bundled in a single commit, which makes c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4f9e16b9c7677419d580a5e85e958f21
https://doi.org/10.1109/ase.2019.00101
https://doi.org/10.1109/ase.2019.00101
Publikováno v:
Internetware
Source code search is one of the most important methods to study and reuse software project. Currently, natural language based code search mainly faces the following two challenges: 1) More accurate search results are required when software projects
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4a654f7e0340730a17af201eb4bcf809
https://doi.org/10.1145/3275219.3275221
https://doi.org/10.1145/3275219.3275221