{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T12:08:44Z","timestamp":1778587724032,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,18]],"date-time":"2024-06-18T00:00:00Z","timestamp":1718668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Nation Science Foundation","award":["2211982"],"award-info":[{"award-number":["2211982"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,18]]},"DOI":"10.1145\/3661167.3661233","type":"proceedings-article","created":{"date-parts":[[2024,6,14]],"date-time":"2024-06-14T12:24:25Z","timestamp":1718367865000},"page":"191-200","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Leveraging Statistical Machine Translation for Code Search"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7464-1597","authenticated-orcid":false,"given":"Hung","family":"Phan","sequence":"first","affiliation":[{"name":"Department of Computer Science, Iowa State University, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8672-5317","authenticated-orcid":false,"given":"Ali","family":"Jannesari","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Iowa State University, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,6,18]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"[n. d.]. Article on treesitter. https:\/\/tinyurl.com\/y2a86znt. Accessed: 2022-6-20."},{"key":"e_1_3_2_2_2_1","unstructured":"[n. d.]. Articles about Machine Translation. https:\/\/tinyurl.com\/5n7d6wrd. Accessed: 2023-5-1."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510125"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"crossref","unstructured":"Saikat Chakraborty Toufique Ahmed Yangruibo Ding Premkumar Devanbu and Baishakhi Ray. 2022. NatGen: Generative pre-training by \"Naturalizing\" source code. arxiv:2206.07585\u00a0[cs.PL]","DOI":"10.1145\/3540250.3549162"},{"key":"e_1_3_2_2_5_1","unstructured":"Le Chen Quazi\u00a0Ishtiaque Mahmud Hung Phan Nesreen\u00a0K. Ahmed and Ali Jannesari. 2023. Learning to Parallelize with OpenMP by Augmented Heterogeneous AST Representation. arxiv:2305.05779\u00a0[cs.LG]"},{"key":"e_1_3_2_2_6_1","unstructured":"Yihong Dong Jiazheng Ding Xue Jiang Ge Li Zhuo Li and Zhi Jin. 2023. CodeScore: Evaluating Code Generation by Learning Code Execution. arxiv:2301.09043\u00a0[cs.SE]"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3551349.3556903"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3311"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","unstructured":"Daya Guo Shuai Lu Nan Duan Yanlin Wang Ming Zhou and Jian Yin. 2022. UniXcoder: Unified Cross-Modal Pre-training for Code Representation. https:\/\/doi.org\/10.48550\/ARXIV.2203.03850","DOI":"10.48550\/ARXIV.2203.03850"},{"key":"e_1_3_2_2_11_1","volume-title":"GraphCodeBERT: Pre-training Code Representations with Data Flow. CoRR abs\/2009.08366","author":"Guo Daya","year":"2020","unstructured":"Daya Guo, Shuo Ren, Shuai Lu, Zhangyin Feng, Duyu Tang, Shujie Liu, Long Zhou, Nan Duan, Alexey Svyatkovskiy, Shengyu Fu, Michele Tufano, Shao\u00a0Kun Deng, Colin\u00a0B. Clement, Dawn Drain, Neel Sundaresan, Jian Yin, Daxin Jiang, and Ming Zhou. 2020. GraphCodeBERT: Pre-training Code Representations with Data Flow. CoRR abs\/2009.08366 (2020). arXiv:2009.08366https:\/\/arxiv.org\/abs\/2009.08366"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3236024.3236051"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.5555\/3304889.3304975"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","unstructured":"Hamel Husain Ho-Hsiang Wu Tiferet Gazit Miltiadis Allamanis and Marc Brockschmidt. 2019. CodeSearchNet Challenge: Evaluating the State of Semantic Code Search. https:\/\/doi.org\/10.48550\/ARXIV.1909.09436","DOI":"10.48550\/ARXIV.1909.09436"},{"key":"e_1_3_2_2_15_1","unstructured":"Seohyun Kim Jinman Zhao Yuchi Tian and Satish Chandra. 2021. Code Prediction by Feeding Trees to Transformers. arxiv:2003.13848\u00a0[cs.SE]"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","unstructured":"Sumith Kulal Panupong Pasupat Kartik Chandra Mina Lee Oded Padon Alex Aiken and Percy Liang. 2019. SPoC: Search-based Pseudocode to Code. https:\/\/doi.org\/10.48550\/ARXIV.1906.04908","DOI":"10.48550\/ARXIV.1906.04908"},{"key":"e_1_3_2_2_17_1","volume-title":"\u00a0H. Hoi","author":"Le Hung","year":"2022","unstructured":"Hung Le, Yue Wang, Akhilesh\u00a0Deepak Gotmare, Silvio Savarese, and Steven C.\u00a0H. Hoi. 2022. CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning. arxiv:2207.01780\u00a0[cs.LG]"},{"key":"e_1_3_2_2_18_1","unstructured":"Haau-Sing Li Mohsen Mesgar Andr\u00e9 F.\u00a0T. Martins and Iryna Gurevych. 2023. Python Code Generation by Asking Clarification Questions. arxiv:2212.09885\u00a0[cs.CL]"},{"key":"e_1_3_2_2_19_1","volume-title":"ROUGE: A Package for Automatic Evaluation of Summaries. In Text Summarization Branches Out","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. ROUGE: A Package for Automatic Evaluation of Summaries. In Text Summarization Branches Out. Association for Computational Linguistics, Barcelona, Spain, 74\u201381. https:\/\/aclanthology.org\/W04-1013"},{"key":"e_1_3_2_2_20_1","unstructured":"Yinhan Liu Myle Ott Naman Goyal Jingfei Du Mandar Joshi Danqi Chen Omer Levy Mike Lewis Luke Zettlemoyer and Veselin Stoyanov. 2019. RoBERTa: A Robustly Optimized BERT Pretraining Approach. arxiv:1907.11692\u00a0[cs.CL]"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/1380584.1380586"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/SANER56733.2023.00021"},{"key":"e_1_3_2_2_23_1","unstructured":"Yuetian Mao Chengcheng Wan Yuze Jiang and Xiaodong Gu. 2023. Self-Supervised Query Reformulation for Code Search. arxiv:2307.00267\u00a0[cs.SE]"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"crossref","unstructured":"Daye Nam Baishakhi Ray Seohyun Kim Xianshan Qu and Satish Chandra. 2022. Predictive Synthesis of API-Centric Code. arxiv:2201.03758\u00a0[cs.SE]","DOI":"10.1145\/3520312.3534866"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2591062.2591072"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3551349.3560434"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2015.36"},{"key":"e_1_3_2_2_28_1","volume-title":"Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311\u2013318","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311\u2013318."},{"key":"e_1_3_2_2_29_1","volume-title":"Evaluating and Optimizing the Effectiveness of Neural Machine Translation in Supporting Code Retrieval Models: A Study on the CAT Benchmark. arXiv preprint arXiv:2308.04693","author":"Phan Hung","year":"2023","unstructured":"Hung Phan and Ali Jannesari. 2023. Evaluating and Optimizing the Effectiveness of Neural Machine Translation in Supporting Code Retrieval Models: A Study on the CAT Benchmark. arXiv preprint arXiv:2308.04693 (2023)."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3180155.3180230"},{"key":"e_1_3_2_2_31_1","unstructured":"Shuo Ren Daya Guo Shuai Lu Long Zhou Shujie Liu Duyu Tang Neel Sundaresan Ming Zhou Ambrosio Blanco and Shuai Ma. 2020. CodeBLEU: a Method for Automatic Evaluation of Code Synthesis. arxiv:2009.10297\u00a0[cs.SE]"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00185"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3549145"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPC58990.2023.00043"},{"key":"e_1_3_2_2_35_1","volume-title":"\u00a0S. Santos","author":"Siddiq Mohammed\u00a0Latif","year":"2023","unstructured":"Mohammed\u00a0Latif Siddiq, Beatrice Casey, and Joanna C.\u00a0S. Santos. 2023. A Lightweight Framework for High-Quality Code Generation. arxiv:2307.08220\u00a0[cs.SE]"},{"key":"e_1_3_2_2_36_1","unstructured":"Nikita Sorokin Dmitry Abulkhanov Sergey Nikolenko and Valentin Malykh. 2023. CCT-Code: Cross-Consistency Training for Multilingual Clone Detection and Code Search. arxiv:2305.11626\u00a0[cs.CL]"},{"key":"e_1_3_2_2_37_1","unstructured":"Zeyu Sun Qihao Zhu Yingfei Xiong Yican Sun Lili Mou and Lu Zhang. 2019. TreeGen: A Tree-Based Transformer Architecture for Code Generation. arxiv:1911.09983\u00a0[cs.LG]"},{"key":"e_1_3_2_2_38_1","volume-title":"Saad Ezzini, Haoye Tian, Yewei Song, Jacques Klein, and Tegawende\u00a0F. Bissyande.","author":"Tang Xunzhu","year":"2023","unstructured":"Xunzhu Tang, zhenghan Chen, Saad Ezzini, Haoye Tian, Yewei Song, Jacques Klein, and Tegawende\u00a0F. Bissyande. 2023. Hyperbolic Code Retrieval: A Novel Approach for Efficient Code Search Using Hyperbolic Space Embeddings. arxiv:2308.15234\u00a0[cs.SE]"},{"key":"e_1_3_2_2_39_1","unstructured":"Sindhu Tipirneni Ming Zhu and Chandan\u00a0K. Reddy. 2023. StructCoder: Structure-Aware Transformer for Code Generation. arxiv:2206.05239\u00a0[cs.LG]"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3238147.3238206"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"crossref","unstructured":"Deze Wang Boxing Chen Shanshan Li Wei Luo Shaoliang Peng Wei Dong and Xiangke Liao. 2023. One Adapter for All Programming Languages? Adapter Tuning for Code Search and Summarization. arxiv:2303.15822\u00a0[cs.SE]","DOI":"10.1109\/ICSE48619.2023.00013"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"crossref","unstructured":"Xin Wang Yasheng Wang Yao Wan Fei Mi Yitong Li Pingyi Zhou Jin Liu Hao Wu Xin Jiang and Qun Liu. 2022. Compilable Neural Code Generation with Compiler Feedback. arxiv:2203.05132\u00a0[cs.CL]","DOI":"10.18653\/v1\/2022.findings-acl.2"},{"key":"e_1_3_2_2_43_1","volume-title":"\u00a0H. Hoi","author":"Wang Yue","year":"2023","unstructured":"Yue Wang, Hung Le, Akhilesh\u00a0Deepak Gotmare, Nghi\u00a0D.Q. Bui, Junnan Li, and Steven C.\u00a0H. Hoi. 2023. CodeT5+: Open Code Large Language Models for Code Understanding and Generation. arXiv preprint (2023)."},{"key":"e_1_3_2_2_44_1","volume-title":"Proceedings of the 39th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a0162)","author":"Wen Yuanbo","year":"2022","unstructured":"Yuanbo Wen, Qi Guo, Qiang Fu, Xiaqing Li, Jianxing Xu, Yanlin Tang, Yongwei Zhao, Xing Hu, Zidong Du, Ling Li, Chao Wang, Xuehai Zhou, and Yunji Chen. 2022. BabelTower: Learning to Auto-parallelized Program Translation. In Proceedings of the 39th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a0162), Kamalika Chaudhuri, Stefanie Jegelka, Le\u00a0Song, Csaba Szepesvari, Gang Niu, and Sivan Sabato (Eds.). PMLR, 23685\u201323700. https:\/\/proceedings.mlr.press\/v162\/wen22b.html"},{"key":"e_1_3_2_2_45_1","unstructured":"Martin Weyssow Xin Zhou Kisub Kim David Lo and Houari Sahraoui. 2023. Exploring Parameter-Efficient Fine-Tuning Techniques for Code Generation with Large Language Models. arxiv:2308.10462\u00a0[cs.SE]"},{"key":"e_1_3_2_2_46_1","volume-title":"Google\u2019s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation. CoRR abs\/1609.08144","author":"Wu Yonghui","year":"2016","unstructured":"Yonghui Wu, Mike Schuster, Zhifeng Chen, Quoc\u00a0V. Le, Mohammad Norouzi, Wolfgang Macherey, Maxim Krikun, Yuan Cao, Qin Gao, Klaus Macherey, Jeff Klingner, Apurva Shah, Melvin Johnson, Xiaobing Liu, Lukasz Kaiser, Stephan Gouws, Yoshikiyo Kato, Taku Kudo, Hideto Kazawa, Keith Stevens, George Kurian, Nishant Patil, Wei Wang, Cliff Young, Jason Smith, Jason Riesa, Alex Rudnick, Oriol Vinyals, Greg Corrado, Macduff Hughes, and Jeffrey Dean. 2016. Google\u2019s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation. CoRR abs\/1609.08144 (2016). arXiv:1609.08144http:\/\/arxiv.org\/abs\/1609.08144"},{"key":"e_1_3_2_2_47_1","volume-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021.","author":"Yue Wang","unstructured":"Wang Yue, Wang Weishi, Joty Shafiq, and Hoi Steven, C.H.2021. CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021."},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"crossref","unstructured":"Shuyan Zhou Uri Alon Sumit Agarwal and Graham Neubig. 2023. CodeBERTScore: Evaluating Code Generation with Pretrained Models of Code. (2023). https:\/\/arxiv.org\/abs\/2302.05527","DOI":"10.18653\/v1\/2023.emnlp-main.859"}],"event":{"name":"EASE 2024: 28th International Conference on Evaluation and Assessment in Software Engineering","location":"Salerno Italy","acronym":"EASE 2024"},"container-title":["Proceedings of the 28th International Conference on Evaluation and Assessment in Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3661167.3661233","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3661167.3661233","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T11:13:25Z","timestamp":1755861205000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3661167.3661233"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,18]]},"references-count":48,"alternative-id":["10.1145\/3661167.3661233","10.1145\/3661167"],"URL":"https:\/\/doi.org\/10.1145\/3661167.3661233","relation":{},"subject":[],"published":{"date-parts":[[2024,6,18]]},"assertion":[{"value":"2024-06-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}