Dung Nguyen Manh, Le Nam Hai, Anh T. V. Dau, Anh-Minh Nguyen, Khanh Nghiem, Jin Guo, Nghi D. Q. Bui. The Vault: A Comprehensive Multilingual Dataset for Advancing Code Understanding and Generation. In Houda Bouamor, Juan Pino 0001, Kalika Bali, editors, Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore, December 6-10, 2023. pages 4763-4788, Association for Computational Linguistics, 2023. [doi]
@inproceedings{ManhHDNNGB23, title = {The Vault: A Comprehensive Multilingual Dataset for Advancing Code Understanding and Generation}, author = {Dung Nguyen Manh and Le Nam Hai and Anh T. V. Dau and Anh-Minh Nguyen and Khanh Nghiem and Jin Guo and Nghi D. Q. Bui}, year = {2023}, url = {https://aclanthology.org/2023.findings-emnlp.316}, researchr = {https://researchr.org/publication/ManhHDNNGB23}, cites = {0}, citedby = {0}, pages = {4763-4788}, booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore, December 6-10, 2023}, editor = {Houda Bouamor and Juan Pino 0001 and Kalika Bali}, publisher = {Association for Computational Linguistics}, isbn = {979-8-89176-061-5}, }