bibliografia.bib

@inproceedings{yao-2018,
 author = {Yao, Ziyu and Weld, Daniel S. and Chen, Wei-Peng and Sun, Huan},
 title = {StaQC: A Systematically Mined Question-Code Dataset from Stack Overflow},
 booktitle = {Proceedings of the 2018 World Wide Web Conference},
 series = {WWW '18},
 year = {2018},
 isbn = {978-1-4503-5639-8},
 location = {Lyon, France},
 pages = {1693--1703},
 numpages = {11},
 url = {https://doi.org/10.1145/3178876.3186081},
 doi = {10.1145/3178876.3186081},
 acmid = {3186081},
 publisher = {International World Wide Web Conferences Steering Committee},
 address = {Republic and Canton of Geneva, Switzerland},
 keywords = {deep neural networks, natural language question answering, question-code pairs, stack overflow},
}

@INPROCEEDINGS{feng-2015, 
author={M. {Feng} and B. {Xiang} and M. R. {Glass} and L. {Wang} and B. {Zhou}}, 
booktitle={2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)}, 
title={Applying deep learning to answer selection: A study and an open task}, 
year={2015}, 
volume={}, 
number={}, 
pages={813-820}, 
keywords={learning (artificial intelligence);question answering (information retrieval);deep learning;nonfactoid question answering task;QA corpus;QA task;insurance domain;Computer architecture;Machine learning;Knowledge discovery;Training;Convolution;Measurement;Insurance;Answer Selection;Question Answering;Convolutional Neural Network (CNN);Deep Learning;Spoken Question Answering System}, 
doi={10.1109/ASRU.2015.7404872}, 
ISSN={}, 
month={Dec},}

@online{sof-2019,
  author = {Stack Exchange, Inc.},
  title = {Stack Exchange Data Dump},
  year = 2019,
  url = {https://archive.org/details/stackexchange},
  urldate = {2019-05-13}
}

@online{bigquery-2019,
  author = {Google},
  title = {Google Cloud BigQuery},
  year = 2019,
  url = {https://cloud.google.com/bigquery/},
  urldate = {2019-05-13}
}

@online{glossary-ml,
  author = {Google},
  title = {Machine Learning Glossary},
  year = 2019,
  url = {https://developers.google.com/machine-learning/glossary/},
  urldate = {2019-05-13}
}

@online{google-question-answering,
  author = {Google AI},
  title = {Open Domain Question Answering},
  year = 2019,
  url = {https://ai.google.com/research/NaturalQuestions},
  urldate = {2019-05-13}
}




@online{stackoverflow-questions-topics-2019,
  author = {stackoverflow},
  title = {What topics can I ask about here?},
  year = 2019,
  url = {https://stackoverflow.com/help/on-topic},
  urldate = {2019-05-13}
}

@inproceedings{iyer-etal-2016-summarizing,
    title = "Summarizing Source Code using a Neural Attention Model",
    author = "Iyer, Srinivasan  and
      Konstas, Ioannis  and
      Cheung, Alvin  and
      Zettlemoyer, Luke",
    booktitle = "Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = aug,
    year = "2016",
    address = "Berlin, Germany",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/P16-1195",
    doi = "10.18653/v1/P16-1195",
    pages = "2073--2083",
}

@inproceedings{Allamanis-method-class-names:2015,
 author = {Allamanis, Miltiadis and Barr, Earl T. and Bird, Christian and Sutton, Charles},
 title = {Suggesting Accurate Method and Class Names},
 booktitle = {Proceedings of the 2015 10th Joint Meeting on Foundations of Software Engineering},
 series = {ESEC/FSE 2015},
 year = {2015},
 isbn = {978-1-4503-3675-8},
 location = {Bergamo, Italy},
 pages = {38--49},
 numpages = {12},
 url = {http://doi.acm.org/10.1145/2786805.2786849},
 doi = {10.1145/2786805.2786849},
 acmid = {2786849},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {Coding conventions, naturalness of software},
}

@article{Proksch:2015,
 author = {Proksch, Sebastian and Lerch, Johannes and Mezini, Mira},
 title = {Intelligent Code Completion with Bayesian Networks},
 journal = {ACM Trans. Softw. Eng. Methodol.},
 issue_date = {December 2015},
 volume = {25},
 number = {1},
 month = dec,
 year = {2015},
 issn = {1049-331X},
 pages = {3:1--3:31},
 articleno = {3},
 numpages = {31},
 url = {http://doi.acm.org/10.1145/2744200},
 doi = {10.1145/2744200},
 acmid = {2744200},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {Content assist, code completion, code recommender, evaluation, integrated development environments, machine learning, productivity},
}

@article{rebecca-2018,
  author    = {Rebecca L. Russell and
               Louis Y. Kim and
               Lei H. Hamilton and
               Tomo Lazovich and
               Jacob A. Harer and
               Onur Ozdemir and
               Paul M. Ellingwood and
               Marc W. McConley},
  title     = {Automated Vulnerability Detection in Source Code Using Deep Representation
               Learning},
  journal   = {CoRR},
  volume    = {abs/1807.04320},
  year      = {2018},
  url       = {http://arxiv.org/abs/1807.04320},
  archivePrefix = {arXiv},
  eprint    = {1807.04320},
  timestamp = {Mon, 13 Aug 2018 16:46:23 +0200},
  biburl    = {https://dblp.org/rec/bib/journals/corr/abs-1807-04320},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@article{Allamanis:2018:SML,
 author = {Allamanis, Miltiadis and Barr, Earl T. and Devanbu, Premkumar and Sutton, Charles},
 title = {A Survey of Machine Learning for Big Code and Naturalness},
 journal = {ACM Comput. Surv.},
 issue_date = {September 2018},
 volume = {51},
 number = {4},
 month = jul,
 year = {2018},
 issn = {0360-0300},
 pages = {81:1--81:37},
 articleno = {81},
 numpages = {37},
 url = {http://doi.acm.org/10.1145/3212695},
 doi = {10.1145/3212695},
 acmid = {3212695},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {Big code, code naturalness, machine learning, software engineering tools},
} 

@online{wikipedia-developers-demographics-2019,
  author = {Wikipedia},
  title = {Software engineering demographics},
  year = 2019,
  url = {https://en.wikipedia.org/wiki/Software_engineering_demographics},
  urldate = {2019-06-10}
}

@online{stackoverflow-survey-2019,
  author = {Stackoverflow},
  title = {Developer Survey Results},
  year = 2019,
  url = {https://insights.stackoverflow.com/survey/2019},
  urldate = {2019-06-10}
}

@inproceedings{Wang-quora:2013,
 author = {Wang, Gang and Gill, Konark and Mohanlal, Manish and Zheng, Haitao and Zhao, Ben Y.},
 title = {Wisdom in the Social Crowd: An Analysis of Quora},
 booktitle = {Proceedings of the 22Nd International Conference on World Wide Web},
 series = {WWW '13},
 year = {2013},
 isbn = {978-1-4503-2035-1},
 location = {Rio de Janeiro, Brazil},
 pages = {1341--1352},
 numpages = {12},
 url = {http://doi.acm.org/10.1145/2488388.2488506},
 doi = {10.1145/2488388.2488506},
 acmid = {2488506},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {graphs, online social networks, q\&\#38;a system},
} 

@INPROCEEDINGS{Vasilescu:2013, 
author={B. {Vasilescu} and V. {Filkov} and A. {Serebrenik}}, 
booktitle={2013 International Conference on Social Computing}, 
title={StackOverflow and GitHub: Associations between Software Development and Crowdsourced Knowledge}, 
year={2013}, 
volume={}, 
number={}, 
pages={188-195}, 
keywords={knowledge based systems;software maintenance;StackOverflow;GitHub;software development;crowdsourced knowledge;social coding repository;online programming question-and-answer community;Software;Rhythm;Electronic mail;Indexes;Communities;Productivity;Merging;software development;crowdsourced knowledge;social media}, 
doi={10.1109/SocialCom.2013.35}, 
ISSN={}, 
month={Sep.},}

@online{wikipedia-quora-2019,
  author = {Wikipedia},
  title = {Quora},
  year = 2019,
  url = {https://pt.wikipedia.org/wiki/Quora},
  urldate = {2019-06-10}
}

@inproceedings{Allamanis-bimodal-source-code-natural-language:2015,
 author = {Allamanis, Miltiadis and Tarlow, Daniel and Gordon, Andrew D. and Wei, Yi},
 title = {Bimodal Modelling of Source Code and Natural Language},
 booktitle = {Proceedings of the 32Nd International Conference on International Conference on Machine Learning - Volume 37},
 series = {ICML'15},
 year = {2015},
 location = {Lille, France},
 pages = {2123--2132},
 numpages = {10},
 url = {http://dl.acm.org/citation.cfm?id=3045118.3045344},
 acmid = {3045344},
 publisher = {JMLR.org},
}

@incollection{Hinton-distributed-representatons:1986,
 author = {Hinton, G. E. and McClelland, J. L. and Rumelhart, D. E.},
 chapter = {Distributed Representations},
 title = {Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vol. 1},
 editor = {Rumelhart, David E. and McClelland, James L. and PDP Research Group, CORPORATE},
 year = {1986},
 isbn = {0-262-68053-X},
 pages = {77--109},
 numpages = {33},
 url = {http://dl.acm.org/citation.cfm?id=104279.104287},
 acmid = {104287},
 publisher = {MIT Press},
 address = {Cambridge, MA, USA},
}

@book{Goodfellow-et-al-2016,
    title={Deep Learning},
    author={Ian Goodfellow and Yoshua Bengio and Aaron Courville},
    publisher={MIT Press},
    note={\url{http://www.deeplearningbook.org}},
    year={2016}
}

@inbook{nndesign:2014:pratical-training-issues,
 author = {Demuth, Howard B. and Beale, Mark H. and De Jess, Orlando and Hagan, Martin T.},
 title = {Neural Network Design},
 year = {2014},
 isbn = {0971732116, 9780971732117},
 edition = {2nd},
 publisher = {Martin Hagan},
 address = {USA},
 chapter = 22,
}

@inproceedings{lai-etal-2018-review,
    title = "A Review on Deep Learning Techniques Applied to Answer Selection",
    author = "Lai, Tuan Manh  and
      Bui, Trung  and
      Li, Sheng",
    booktitle = "Proceedings of the 27th International Conference on Computational Linguistics",
    month = aug,
    year = "2018",
    address = "Santa Fe, New Mexico, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/C18-1181",
    pages = "2132--2144",
    abstract = "Given a question and a set of candidate answers, answer selection is the task of identifying which of the candidates answers the question correctly. It is an important problem in natural language processing, with applications in many areas. Recently, many deep learning based methods have been proposed for the task. They produce impressive performance without relying on any feature engineering or expensive external resources. In this paper, we aim to provide a comprehensive review on deep learning methods applied to answer selection.",
}

@article{tan-lstm-qa,
  author    = {Ming Tan and
               Cicero dos Santos and
               Bing Xiang and
               Bowen Zhou},
  title     = {LSTM-based Deep Learning Models for non-factoid answer selection},
  journal   = {CoRR},
  volume    = {abs/1511.04108},
  year      = {2015},
  url       = {http://arxiv.org/abs/1511.04108},
  archivePrefix = {arXiv},
  eprint    = {1511.04108},
  timestamp = {Mon, 13 Aug 2018 16:46:33 +0200},
  biburl    = {https://dblp.org/rec/bib/journals/corr/TanXZ15},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@inproceedings{Gu-deep-code-search:2018,
 author = {Gu, Xiaodong and Zhang, Hongyu and Kim, Sunghun},
 title = {Deep Code Search},
 booktitle = {Proceedings of the 40th International Conference on Software Engineering},
 series = {ICSE '18},
 year = {2018},
 isbn = {978-1-4503-5638-1},
 location = {Gothenburg, Sweden},
 pages = {933--944},
 numpages = {12},
 url = {http://doi.acm.org/10.1145/3180155.3180167},
 doi = {10.1145/3180155.3180167},
 acmid = {3180167},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {code search, deep learning, joint embedding},
}

@inproceedings{Sachdev-neural-code-search:2018,
 author = {Sachdev, Saksham and Li, Hongyu and Luan, Sifei and Kim, Seohyun and Sen, Koushik and Chandra, Satish},
 title = {Retrieval on Source Code: A Neural Code Search},
 booktitle = {Proceedings of the 2Nd ACM SIGPLAN International Workshop on Machine Learning and Programming Languages},
 series = {MAPL 2018},
 year = {2018},
 isbn = {978-1-4503-5834-7},
 location = {Philadelphia, PA, USA},
 pages = {31--41},
 numpages = {11},
 url = {http://doi.acm.org/10.1145/3211346.3211353},
 doi = {10.1145/3211346.3211353},
 acmid = {3211353},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {TF-IDF, code search, word-embedding},
}

@inproceedings{cambronero-deep-learning-code-search:2019,
author = {Cambronero, Jose and Li, Hongyu and Kim, Seohyun and Sen, Koushik and Chandra, Satish},
title = {When Deep Learning Met Code Search},
year = {2019},
isbn = {9781450355728},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3338906.3340458},
doi = {10.1145/3338906.3340458},
booktitle = {Proceedings of the 2019 27th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering},
pages = {964–974},
numpages = {11},
keywords = {joint embedding, neural networks, code search},
location = {Tallinn, Estonia},
series = {ESEC/FSE 2019}
}

@ARTICLE{shao-answer-selection:2019, 
author={T. {Shao} and Y. {Guo} and H. {Chen} and Z. {Hao}}, 
journal={IEEE Access}, 
title={Transformer-Based Neural Network for Answer Selection in Question Answering}, 
year={2019}, 
volume={7}, 
number={}, 
pages={26146-26156}, 
keywords={question answering (information retrieval);recurrent neural nets;text analysis;question answering system;QA-TF;sentence embedding;BiLSTM;bidirectional long short-term memory;answer selection;transformer-based neural network;Task analysis;Feature extraction;Knowledge discovery;Artificial neural networks;Tools;Natural language processing;Answer selection;deep learning;question answering;Transformer}, 
doi={10.1109/ACCESS.2019.2900753}, 
ISSN={2169-3536}, 
month={},}

@inproceedings{Chen-bi-variational-autoencoder:2018,
 author = {Chen, Qingying and Zhou, Minghui},
 title = {A Neural Framework for Retrieval and Summarization of Source Code},
 booktitle = {Proceedings of the 33rd ACM/IEEE International Conference on Automated Software Engineering},
 series = {ASE 2018},
 year = {2018},
 isbn = {978-1-4503-5937-5},
 location = {Montpellier, France},
 pages = {826--831},
 numpages = {6},
 url = {http://doi.acm.org/10.1145/3238147.3240471},
 doi = {10.1145/3238147.3240471},
 acmid = {3240471},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {Code retrieval, code summarization, neural framework},
}

@inproceedings{Yao-coacor:2019,
 author = {Yao, Ziyu and Peddamail, Jayavardhan Reddy and Sun, Huan},
 title = {CoaCor: Code Annotation for Code Retrieval with Reinforcement Learning},
 booktitle = {The World Wide Web Conference},
 series = {WWW '19},
 year = {2019},
 isbn = {978-1-4503-6674-8},
 location = {San Francisco, CA, USA},
 pages = {2203--2214},
 numpages = {12},
 url = {http://doi.acm.org/10.1145/3308558.3313632},
 doi = {10.1145/3308558.3313632},
 acmid = {3313632},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {Code Annotation, Code Retrieval, Reinforcement Learning},
}

@misc{mikolov2013distributed,
title	= {Efficient Estimation of Word Representations in Vector Space},
author	= {Tomas Mikolov and Kai Chen and Greg S. Corrado and Jeffrey Dean},
year	= {2013},
URL	= {http://arxiv.org/abs/1301.3781}
}

@online{scikit-learn-tsne-2019,
  author = {scikit-learn},
  title = {sklearn.manifold.TSNE},
  year = 2019,
  url = {https://scikit-learn.org/stable/modules/generated/sklearn.manifold.TSNE.html},
  urldate = {2019-09-13}
}

@online{quora-tsne-2019,
  author = {Simba Khadder},
  title = {How does t-SNE work in simple words?},
  year = 2019,
  url = {https://www.quora.com/How-does-t-SNE-work-in-simple-words},
  urldate = {2019-09-13}
}

@online{wikipedia-docstring-2019,
  author = {Wikipedia},
  title = {Docstring},
  year = 2019,
  url = {https://en.wikipedia.org/wiki/Docstring},
  urldate = {2019-09-13}
}

@inproceedings{marcelo-vem-2019,
 author = {Marcelo de Rezende Martins and Marco Aurélio Gerosa},
 title = {Um estudo preliminar sobre o uso de uma arquitetura deep learning para seleção de respostas no problema de recuperação de código-fonte},
 booktitle = {Anais do VII Workshop on Software Visualization, Evolution and Maintenance (VEM)},
 location = {Salvador},
 year = {2019},
 keywords = {},
 pages = {94--101},
 publisher = {SBC},
 address = {Porto Alegre, RS, Brasil},
 doi = {10.5753/vem.2019.7589},
 url = {https://sol.sbc.org.br/index.php/vem/article/view/7589}
}

@article{Zhang:2019:deep-learning-recommender-survey,
 author = {Zhang, Shuai and Yao, Lina and Sun, Aixin and Tay, Yi},
 title = {Deep Learning Based Recommender System: A Survey and New Perspectives},
 journal = {ACM Comput. Surv.},
 issue_date = {February 2019},
 volume = {52},
 number = {1},
 month = feb,
 year = {2019},
 issn = {0360-0300},
 pages = {5:1--5:38},
 articleno = {5},
 numpages = {38},
 url = {http://doi.acm.org/10.1145/3285029},
 doi = {10.1145/3285029},
 acmid = {3285029},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {Recommender system, deep learning, survey},
}

@online{colab-2019,
  author = {Google},
  title = {Colaboratory},
  year = 2019,
  url = {https://research.google.com/colaboratory/faq.html},
  urldate = {2019-09-13}
}

@online{jupyter-2019,
  author = {Jupyter},
  title = {Jupyter Notebook},
  year = 2019,
  url = {https://jupyter-notebook.readthedocs.io/en/latest/},
  urldate = {2019-09-13}
}

@online{joshua-kim-cnn-understanding-word-embeddings-2019,
  author = {Joshua Kim},
  title = {Understanding how Convolutional Neural Network (CNN) perform text classification with word embeddings},
  year = 2019,
  url = {http://www.joshuakim.io/understanding-how-convolutional-neural-network-cnn-perform-text-classification-with-word-embeddings/},
  urldate = {2019-09-13}
}

@online{wikipedia-git-2019,
  author = {Wikipedia},
  title = {Git},
  year = 2019,
  url = {https://en.wikipedia.org/wiki/Git},
  urldate = {2019-09-13}
}

@ARTICLE{tom-young:trends-deep-learning-nlp, 
author={T. {Young} and D. {Hazarika} and S. {Poria} and E. {Cambria}}, journal={IEEE Computational Intelligence Magazine}, title={Recent Trends in Deep Learning Based Natural Language Processing [Review Article]}, year={2018}, volume={13}, number={3}, pages={55-75},}


@inproceedings{zhang-guide-convolutional-cnn-embedding-ilustration:2015,
    title = "A Sensitivity Analysis of (and Practitioners{'} Guide to) Convolutional Neural Networks for Sentence Classification",
    author = "Zhang, Ye  and
      Wallace, Byron",
    booktitle = "Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
    month = nov,
    year = "2017",
    address = "Taipei, Taiwan",
    publisher = "Asian Federation of Natural Language Processing",
    url = "https://www.aclweb.org/anthology/I17-1026",
    pages = "253--263",
    abstract = "Convolutional Neural Networks (CNNs) have recently achieved remarkably strong performance on the practically important task of sentence classification (Kim, 2014; Kalchbrenner et al., 2014; Johnson and Zhang, 2014; Zhang et al., 2016). However, these models require practitioners to specify an exact model architecture and set accompanying hyperparameters, including the filter region size, regularization parameters, and so on. It is currently unknown how sensitive model performance is to changes in these configurations for the task of sentence classification. We thus conduct a sensitivity analysis of one-layer CNNs to explore the effect of architecture components on model performance; our aim is to distinguish between important and comparatively inconsequential design decisions for sentence classification. We focus on one-layer CNNs (to the exclusion of more complex models) due to their comparative simplicity and strong empirical performance, which makes it a modern standard baseline method akin to Support Vector Machine (SVMs) and logistic regression. We derive practical advice from our extensive empirical results for those interested in getting the most out of CNNs for sentence classification in real world settings.",
}



@inproceedings{masudur-developers-use-google-code-retrieval:2018,
author = {Rahman, Md Masudur and Barson, Jed and Paul, Sydney and Kayani, Joshua and Lois, Federico Andr\'{e}s and Quezada, Sebasti\'{a}n Fernandez and Parnin, Christopher and Stolee, Kathryn T. and Ray, Baishakhi},
title = {Evaluating How Developers Use General-Purpose Web-Search for Code Retrieval},
year = {2018},
isbn = {9781450357166},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3196398.3196425},
doi = {10.1145/3196398.3196425},
booktitle = {Proceedings of the 15th International Conference on Mining Software Repositories},
pages = {465–475},
numpages = {11},
location = {Gothenburg, Sweden},
series = {MSR ’18}
}

@online{husain-github-semantic-search-code-2019,
  author = {Hamel Husain and Ho-Hsiang Wu},
  title = {How To Create Natural Language Semantic Search For Arbitrary Objects With Deep Learning},
  year = 2018,
  url = {https://towardsdatascience.com/semantic-code-search-3cd6d244a39c},
  urldate = {2020-04-13}
}

@online{casi-newell-sentence-length-2018,
  author = {Casi Newell},
  title = {Editing Tip: Sentence Length},
  year = 2018,
  url = {https://www.aje.com/en/arc/editing-tip-sentence-length/},
  urldate = {2020-04-13}
}

@INPROCEEDINGS{tang-hybrid-deep-representation-2018, author={D. {Tang} and W. {Rong} and L. {Shi} and H. {Yang} and Z. {Xiong}}, booktitle={2018 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC)}, title={A Hybrid of Deep Sentence Representation and Local Feature Representation Model for Question Answer Selection}, year={2018}, volume={}, number={}, pages={280-2803},}

@article{wen-joint-modeling-question-answer-2019,
title = "Joint modeling of users, questions and answers for answer selection in CQA",
journal = "Expert Systems with Applications",
volume = "118",
pages = "563 - 572",
year = "2019",
issn = "0957-4174",
doi = "https://doi.org/10.1016/j.eswa.2018.10.038",
url = "http://www.sciencedirect.com/science/article/pii/S0957417418306961",
author = "Jiahui Wen and Hongkui Tu and Xiaohui Cheng and Renquan Xie and Wei Yin",
keywords = "Answer selection, User modelling, Attentive neural network",
abstract = "In this paper, we propose solutions to advance answer selection in Community Question Answering (CQA). Automatically selecting correct answers can significantly improve intelligence for CQA, as users are not required to browse the large quantity of texts and select the right answers manually. Also, automatic answers selection can minimize the time for satisfying users seeking the correct answers and maximize user engagement with the site. Unlike previous works, we propose a hybrid attention mechanism to model question-answer pairs. Specifically, for each word, we calculate the intra-sentence attention indicating its local importance and the inter-sentence attention implying its importance to the counterpart sentence. The inter-sentence attention is based on the interactions between question-answer pairs, and the combination of these two attention mechanisms enables us to align the most informative parts in question-answer pairs for sentence matching. Additionally, we exploit user information for answer selection due to the fact that users are more likely to provide correct answers in their areas of expertise. We model users from their written answers to alleviate data sparsity problem, and then learn user representations according to the informative parts in sentences that are useful for question-answer matching task. This mean of modelling users can bridge the semantic gap between different users, as similar users may have the same way of wording their answers. The representations of users, questions and answers are learnt in an end-to-end neural network in a mean that best explains the interrelation between question-answer pairs. We validate the proposed model on a public dataset, and demonstrate its advantages over the baselines with thorough experiments."
}

@inproceedings{sergey-batch-normalization-2015,
author = {Ioffe, Sergey and Szegedy, Christian},
title = {Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift},
year = {2015},
publisher = {JMLR.org},
booktitle = {Proceedings of the 32nd International Conference on International Conference on Machine Learning - Volume 37},
pages = {448–456},
numpages = {9},
location = {Lille, France},
series = {ICML’15}
}

@inproceedings{rajpurkar-etal-2016-squad,
    title = "{SQ}u{AD}: 100,000+ Questions for Machine Comprehension of Text",
    author = "Rajpurkar, Pranav  and
      Zhang, Jian  and
      Lopyrev, Konstantin  and
      Liang, Percy",
    booktitle = "Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2016",
    address = "Austin, Texas",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/D16-1264",
    doi = "10.18653/v1/D16-1264",
    pages = "2383--2392",
}

@article{theodora-introductory-programming-python-2015,
author = {Koulouri, Theodora and Lauria, Stanislao and Macredie, Robert D.},
title = {Teaching Introductory Programming: A Quantitative Evaluation of Different Approaches},
year = {2015},
issue_date = {February 2015},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
volume = {14},
number = {4},
url = {https://doi.org/10.1145/2662412},
doi = {10.1145/2662412},
journal = {ACM Trans. Comput. Educ.},
month = dec,
articleno = {Article 26},
numpages = {28},
keywords = {teaching strategies, novice programmers, CS1, programming languages, learning programming, formative feedback, problem solving, Empirical studies}
}

@inproceedings{devlin-etal-2019-bert,
    title = "{BERT}: Pre-training of Deep Bidirectional Transformers for Language Understanding",
    author = "Devlin, Jacob  and
      Chang, Ming-Wei  and
      Lee, Kenton  and
      Toutanova, Kristina",
    booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
    month = jun,
    year = "2019",
    address = "Minneapolis, Minnesota",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/N19-1423",
    doi = "10.18653/v1/N19-1423",
    pages = "4171--4186",
    abstract = "We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models (Peters et al., 2018a; Radford et al., 2018), BERT is designed to pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers. As a result, the pre-trained BERT model can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks, such as question answering and language inference, without substantial task-specific architecture modifications. BERT is conceptually simple and empirically powerful. It obtains new state-of-the-art results on eleven natural language processing tasks, including pushing the GLUE score to 80.5 (7.7 point absolute improvement), MultiNLI accuracy to 86.7{\%} (4.6{\%} absolute improvement), SQuAD v1.1 question answering Test F1 to 93.2 (1.5 point absolute improvement) and SQuAD v2.0 Test F1 to 83.1 (5.1 point absolute improvement).",
}

@inproceedings{yang2019xlNet,
  title = {XLNet: Generalized Autoregressive Pretraining for Language Understanding},
  author = {Yang, Zhilin and Dai, Zihang and Yang, Yiming and Carbonell, Jaime and Salakhutdinov, Russ R and Le, Quoc V},
  booktitle = {Advances in Neural Information Processing Systems 32},
  pages = {5754--5764},
  year = {2019},
  publisher = {Curran Associates, Inc.},
  url = {http://papers.nips.cc/paper/8812-xlnet-generalized-autoregressive-pretraining-for-language-understanding.pdf}
}

@inproceedings{park-regarding-margin-loss:2017,
author = {Kang, Myeong K. and Park, Kyo H. and Kim, Seong W. and Kim, Min J. and Lee, Sang C.},
title = {Classification Performance Analysis Regarding Margin of Energy-Based Model},
year = {2017},
isbn = {9781450348669},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3178264.3178280},
doi = {10.1145/3178264.3178280},
booktitle = {Proceedings of the 2017 International Conference on Industrial Design Engineering},
pages = {34–37},
numpages = {4},
keywords = {negative-log-likelihood loss, triplet loss, energy based models, hinge loss, margin},
location = {Dubai, United Arab Emirates},
series = {ICIDE 2017}
}
@online{wikipedia-tensorflow-2020,
  author = {Wikipedia},
  title = {Tensorflow},
  year = 2020,
  url = {https://pt.wikipedia.org/wiki/TensorFlow},
  urldate = {2020-04-13}
}
@online{wikipedia-keras-2020,
  author = {Wikipedia},
  title = {Keras},
  year = 2020,
  url = {https://en.wikipedia.org/wiki/Keras},
  urldate = {2020-04-13}
}

@article{bengio-hyper-parameter-optimization-2012,
  author  = {James Bergstra and Yoshua Bengio},
  title   = {Random Search for Hyper-Parameter Optimization},
  journal = {Journal of Machine Learning Research},
  year    = {2012},
  volume  = {13},
  number  = {10},
  pages   = {281-305},
  url     = {http://jmlr.org/papers/v13/bergstra12a.html}
}

@InProceedings{kun-learning-to-rank:2018,
author = {He, Kun and Cakir, Fatih and Adel Bargal, Sarah and Sclaroff, Stan},
title = {Hashing as Tie-Aware Learning to Rank},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2018}
}

@article{hasson-direct-fit-to-nature-evolutionary-perspective-ann:2020,
title = "Direct Fit to Nature: An Evolutionary Perspective on Biological and Artificial Neural Networks",
journal = "Neuron",
volume = "105",
number = "3",
pages = "416 - 434",
year = "2020",
issn = "0896-6273",
doi = "https://doi.org/10.1016/j.neuron.2019.12.002",
url = "http://www.sciencedirect.com/science/article/pii/S089662731931044X",
author = "Uri Hasson and Samuel A. Nastase and Ariel Goldstein",
keywords = "evolution, experimental design, interpolation, learning, neural networks",
abstract = "Summary
Evolution is a blind fitting process by which organisms become adapted to their environment. Does the brain use similar brute-force fitting processes to learn how to perceive and act upon the world? Recent advances in artificial neural networks have exposed the power of optimizing millions of synaptic weights over millions of observations to operate robustly in real-world contexts. These models do not learn simple, human-interpretable rules or representations of the world; rather, they use local computations to interpolate over task-relevant manifolds in a high-dimensional parameter space. Counterintuitively, similar to evolutionary processes, over-parameterized models can be simple and parsimonious, as they provide a versatile, robust solution for learning a diverse set of functions. This new family of direct-fit models present a radical challenge to many of the theoretical assumptions in psychology and neuroscience. At the same time, this shift in perspective establishes unexpected links with developmental and ecological psychology."
}

@inproceedings{sadowski-how-developers-search-for-code-case-study:2015,
author = {Sadowski, Caitlin and Stolee, Kathryn T. and Elbaum, Sebastian},
title = {How Developers Search for Code: A Case Study},
year = {2015},
isbn = {9781450336758},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/2786805.2786855},
doi = {10.1145/2786805.2786855},
booktitle = {Proceedings of the 2015 10th Joint Meeting on Foundations of Software Engineering},
pages = {191–201},
numpages = {11},
keywords = {user evaluation, code search, developer tools},
location = {Bergamo, Italy},
series = {ESEC/FSE 2015}
}

@article{silver-mastering-the-game-go:2016,
  added-at = {2016-03-11T14:36:05.000+0100},
  author = {Silver, David and Huang, Aja and Maddison, Chris J. and Guez, Arthur and Sifre, Laurent and van den Driessche, George and Schrittwieser, Julian and Antonoglou, Ioannis and Panneershelvam, Veda and Lanctot, Marc and Dieleman, Sander and Grewe, Dominik and Nham, John and Kalchbrenner, Nal and Sutskever, Ilya and Lillicrap, Timothy and Leach, Madeleine and Kavukcuoglu, Koray and Graepel, Thore and Hassabis, Demis},
  doi = {10.1038/nature16961},
  journal = {Nature},
  keywords = {baduk go google},
  month = jan,
  number = 7587,
  pages = {484--489},
  publisher = {Nature Publishing Group},
  timestamp = {2016-03-11T14:37:40.000+0100},
  title = {Mastering the Game of {Go} with Deep Neural Networks and Tree Search},
  volume = 529,
  year = 2016
}

@article{allahyari-text-summarization-2017,
  author    = {Mehdi Allahyari and
               Seyed Amin Pouriyeh and
               Mehdi Assefi and
               Saeid Safaei and
               Elizabeth D. Trippe and
               Juan B. Gutierrez and
               Krys Kochut},
  title     = {Text Summarization Techniques: {A} Brief Survey},
  journal   = {CoRR},
  volume    = {abs/1707.02268},
  year      = {2017}
  
  
  
}

@article{what-developers-search-for-on-the-web:xia:2017,
author = {Xia, Xin and Bao, Lingfeng and Lo, David and Kochhar, Pavneet Singh and Hassan, Ahmed E. and Xing, Zhenchang},
title = {What Do Developers Search for on the Web?},
year = {2017},
issue_date = {December  2017},
publisher = {Kluwer Academic Publishers},
address = {USA},
volume = {22},
number = {6},
issn = {1382-3256},
url = {https://doi.org/10.1007/s10664-017-9514-4},
doi = {10.1007/s10664-017-9514-4},
journal = {Empirical Softw. Engg.},
month = dec,
pages = {3149–3185},
numpages = {37},
keywords = {Empirical study, Understanding, Search task, Survey}
}

@inproceedings{towards-summarizing-source-code-search:marin:2020,
author = {Marin, Victor J. and Bansal, Iti and Rivero, Carlos R.},
title = {Towards Summarizing Program Statements in Source Code Search},
year = {2020},
isbn = {9781450368667},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3341105.3374055},
doi = {10.1145/3341105.3374055},
booktitle = {Proceedings of the 35th Annual ACM Symposium on Applied Computing},
pages = {118–120},
numpages = {3},
keywords = {program dependence graph, community detection, approximate graph alignment, source code search},
location = {Brno, Czech Republic},
series = {SAC ’20}
}

@INPROCEEDINGS{yan-benchmark-code-search-information-retrieval-deep-learning:2020,
  author={S. {Yan} and H. {Yu} and Y. {Chen} and B. {Shen} and L. {Jiang}},
  booktitle={2020 IEEE 27th International Conference on Software Analysis, Evolution and Reengineering (SANER)}, 
  title={Are the Code Snippets What We Are Searching for? A Benchmark and an Empirical Study on Code Search with Natural-Language Queries}, 
  year={2020},
  volume={},
  number={},
  pages={344-354},}
  
  @article{guo-deep-look-into-neural-ranking-models:2019,
title = "A Deep Look into neural ranking models for information retrieval",
journal = "Information Processing & Management",
pages = "102067",
year = "2019",
issn = "0306-4573",
doi = "https://doi.org/10.1016/j.ipm.2019.102067",
url = "http://www.sciencedirect.com/science/article/pii/S0306457319302390",
author = "Jiafeng Guo and Yixing Fan and Liang Pang and Liu Yang and Qingyao Ai and Hamed Zamani and Chen Wu and W. Bruce Croft and Xueqi Cheng",
keywords = "Neural ranking model, Information retrieval, Survey",
abstract = "Ranking models lie at the heart of research on information retrieval (IR). During the past decades, different techniques have been proposed for constructing ranking models, from traditional heuristic methods, probabilistic methods, to modern machine learning methods. Recently, with the advance of deep learning technology, we have witnessed a growing body of work in applying shallow or deep neural networks to the ranking problem in IR, referred to as neural ranking models in this paper. The power of neural ranking models lies in the ability to learn from the raw text inputs for the ranking problem to avoid many limitations of hand-crafted features. Neural networks have sufficient capacity to model complicated tasks, which is needed to handle the complexity of relevance estimation in ranking. Since there have been a large variety of neural ranking models proposed, we believe it is the right time to summarize the current status, learn from existing methodologies, and gain some insights for future development. In contrast to existing reviews, in this survey, we will take a deep look into the neural ranking models from different dimensions to analyze their underlying assumptions, major design principles, and learning strategies. We compare these models through benchmark tasks to obtain a comprehensive empirical understanding of the existing techniques. We will also discuss what is missing in the current literature and what are the promising and desired future directions."
}

@InProceedings{wu-sql-rank-listwise-approach:2018,
  title = 	 {{SQL}-Rank: A Listwise Approach to Collaborative Ranking},
  author = 	 {Wu, Liwei and Hsieh, Cho-Jui and Sharpnack, James},
  booktitle = 	 {Proceedings of the 35th International Conference on Machine Learning},
  pages = 	 {5315--5324},
  year = 	 {2018},
  editor = 	 {Dy, Jennifer and Krause, Andreas},
  volume = 	 {80},
  series = 	 {Proceedings of Machine Learning Research},
  address = 	 {Stockholmsmässan, Stockholm Sweden},
  month = 	 {10--15 Jul},
  publisher = 	 {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v80/wu18c/wu18c.pdf},
  url = 	 {http://proceedings.mlr.press/v80/wu18c.html},
  abstract = 	 {In this paper, we propose a listwise approach for constructing user-specific rankings in recommendation systems in a collaborative fashion. We contrast the listwise approach to previous pointwise and pairwise approaches, which are based on treating either each rating or each pairwise comparison as an independent instance respectively. By extending the work of ListNet (Cao et al., 2007), we cast listwise collaborative ranking as maximum likelihood under a permutation model which applies probability mass to permutations based on a low rank latent score matrix. We present a novel algorithm called SQL-Rank, which can accommodate ties and missing data and can run in linear time. We develop a theoretical framework for analyzing listwise ranking methods based on a novel representation theory for the permutation model. Applying this framework to collaborative ranking, we derive asymptotic statistical rates as the number of users and items grow together. We conclude by demonstrating that our SQL-Rank method often outperforms current state-of-the-art algorithms for implicit feedback such as Weighted-MF and BPR and achieve favorable results when compared to explicit feedback algorithms such as matrix factorization and collaborative ranking.}
}

@InProceedings{gutmann-nce-noise-contrastive-estimation-2010,
  title = 	 {Noise-contrastive estimation: A new estimation principle for unnormalized statistical models},
  author = 	 {Michael Gutmann and Aapo Hyvärinen},
  booktitle = 	 {Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics},
  pages = 	 {297--304},
  year = 	 {2010},
  editor = 	 {Yee Whye Teh and Mike Titterington},
  volume = 	 {9},
  series = 	 {Proceedings of Machine Learning Research},
  address = 	 {Chia Laguna Resort, Sardinia, Italy},
  month = 	 {13--15 May},
  publisher = 	 {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v9/gutmann10a/gutmann10a.pdf},
  url = 	 {http://proceedings.mlr.press/v9/gutmann10a.html},
  abstract = 	 {We present a new estimation principle for parameterized statistical models. The idea is to perform nonlinear logistic regression to discriminate between the observed data and some artificially generated noise, using the model log-density function in the regression nonlinearity.  We show that this leads to a consistent (convergent) estimator of the parameters, and analyze the asymptotic variance.  In particular, the method is shown to directly work for unnormalized models, i.e. models where the density function does not integrate to one. The normalization constant can be estimated just like any other parameter. For a tractable ICA model, we compare the method with other estimation methods that can be used to learn unnormalized models, including score matching, contrastive divergence, and maximum-likelihood where the normalization constant is estimated with importance sampling. Simulations show that noise-contrastive estimation offers the best trade-off between computational and statistical efficiency. The method is then applied to the modeling of natural images: We show that the method can successfully estimate a large-scale two-layer model and a Markov random field.}
}

@incollection{attention-is-all-you-need-2017,
title = {Attention is All you Need},
author = {Vaswani, Ashish and Shazeer, Noam and Parmar, Niki and Uszkoreit, Jakob and Jones, Llion and Gomez, Aidan N and Kaiser, \L ukasz and Polosukhin, Illia},
booktitle = {Advances in Neural Information Processing Systems 30},
editor = {I. Guyon and U. V. Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
pages = {5998--6008},
year = {2017},
publisher = {Curran Associates, Inc.},
url = {http://papers.nips.cc/paper/7181-attention-is-all-you-need.pdf}
}

@incollection{devise-deep-visual-semantic-embedding-frome-2013,
title = {DeViSE: A Deep Visual-Semantic Embedding Model},
author = {Frome, Andrea and Corrado, Greg S and Shlens, Jon and Bengio, Samy and Dean, Jeff and Ranzato, Marc\textquotesingle Aurelio and Mikolov, Tomas},
booktitle = {Advances in Neural Information Processing Systems 26},
editor = {C. J. C. Burges and L. Bottou and M. Welling and Z. Ghahramani and K. Q. Weinberger},
pages = {2121--2129},
year = {2013},
publisher = {Curran Associates, Inc.},
url = {http://papers.nips.cc/paper/5204-devise-a-deep-visual-semantic-embedding-model.pdf}
}

@misc{martins2020concra,
    title={CoNCRA: A Convolutional Neural Network Code Retrieval Approach},
    author={Marcelo de Rezende Martins and Marco A. Gerosa},
    year={2020},
    eprint={2009.01959},
    howpublished={\url{https://arxiv.org/abs/2009.01959}},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

@inproceedings{luong-etal-2015-effective,
    title = "Effective Approaches to Attention-based Neural Machine Translation",
    author = "Luong, Thang  and
      Pham, Hieu  and
      Manning, Christopher D.",
    booktitle = "Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing",
    month = sep,
    year = "2015",
    address = "Lisbon, Portugal",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/D15-1166",
    doi = "10.18653/v1/D15-1166",
    pages = "1412--1421",
}