Publications by Jaeho Shin

@article{abc,
	abstract = {Populating a database with unstructured information is a long-standing problem in industry and research that encompasses problems of extraction, cleaning, and integration. Recent names used for this problem include dealing with dark data and knowledge base construction (KBC). In this work, we describe DeepDive, a system that combines database and machine learning ideas to help develop KBC systems, and we present techniques to make the KBC process more efficient. We observe that the KBC process is iterative, and we develop techniques to incrementally produce inference results for KBC systems. We propose two methods for incremental inference, based respectively on sampling and variational techniques. We also study the tradeoff space of these methods and develop a simple rule-based optimizer. DeepDive includes all of these contributions, and we evaluate DeepDive on five KBC systems, showing that it can speed up KBC inference tasks by up to two orders of magnitude with negligible impact on quality.},
	author = {Christopher De Sa and Alexander Ratner and Christopher R{\'e} and Jaeho Shin and Feiran Wang and Sen Wu and Ce Zhang},
	journal = {VLDB J.},
	title = {Incremental knowledge base construction using DeepDive.},
	url = {http://dx.doi.org/10.1007/s00778-016-0437-2},
	year = {2017}
}

@inproceedings{abc,
	abstract = {The dark data extraction or knowledge base construction (KBC) problem is to populate a SQL database with information from unstructured data sources including emails, webpages, and pdf reports. KBC is a long-standing problem in industry and research that encompasses problems of data extraction, cleaning, and integration. We describe DeepDive, a system that combines database and machine learning ideas to help develop KBC systems. The key idea in DeepDive is that statistical inference and machine learning are key tools to attack classical data problems in extraction, cleaning, and integration in a unified and more effective manner. DeepDive programs are declarative in that one cannot write probabilistic inference algorithms; instead, one interacts by defining features or rules about the domain. A key reason for this design choice is to enable domain experts to build their own KBC systems. We present the applications, abstractions, and techniques of DeepDive employed to accelerate construction of KBC systems.},
	author = {Ce Zhang and Christopher R{\'e} and Michael J. Cafarella and Jaeho Shin and Feiran Wang and Sen Wu},
	booktitle = {Commun. ACM},
	title = {DeepDive: declarative knowledge base construction.},
	url = {http://doi.acm.org/10.1145/3060586},
	venue = {-},
	year = {2017}
}

@inproceedings{abc,
	abstract = {DeepDive is a system for extracting relational databases from dark data: the mass of text, tables, and images that are widely collected and stored but which cannot be exploited by standard relational tools. If the information in dark data - scientific papers, Web classified ads, customer service notes, and so on - were instead in a relational database, it would give analysts a massive and valuable new set of "big data." DeepDive is distinctive when compared to previous information extraction systems in its ability to obtain very high precision and recall at reasonable engineering cost; in a number of applications, we have used DeepDive to create databases with accuracy that meets that of human annotators. To date we have successfully deployed DeepDive to create data-centric applications for insurance, materials science, genomics, paleontologists, law enforcement, and others. The data unlocked by DeepDive represents a massive opportunity for industry, government, and scientific researchers. DeepDive is enabled by an unusual design that combines large-scale probabilistic inference with a novel developer interaction cycle. This design is enabled by several core innovations around probabilistic training and inference.},
	author = {Ce Zhang and Jaeho Shin and Christopher R{\'e} and Michael J. Cafarella and Feng Niu},
	booktitle = {Proceedings of the 2016 International Conference on Management of Data, SIGMOD Conference 2016},
	title = {Extracting Databases from Dark Data with DeepDive.},
	url = {http://doi.acm.org/10.1145/2882903.2904442},
	venue = {San Francisco, CA, USA},
	year = {2016}
}

@article{abc,
	abstract = {The dark data extraction or knowledge base construction (KBC) problem is to populate a SQL database with information from unstructured data sources including emails, webpages, and pdf reports. KBC is a long-standing problem in industry and research that encompasses problems of data extraction, cleaning, and integration. We describe DeepDive, a system that combines database and machine learning ideas to help develop KBC systems. The key idea in DeepDive is that statistical inference and machine learning are key tools to attack classical data problems in extraction, cleaning, and integration in a unified and more effective manner. DeepDive programs are declarative in that one cannot write probabilistic inference algorithms; instead, one interacts by defining features or rules about the domain. A key reason for this design choice is to enable domain experts to build their own KBC systems. We present the applications, abstractions, and techniques of DeepDive employed to accelerate construction of KBC systems.},
	author = {Christopher De Sa and Alexander Ratner and Christopher R{\'e} and Jaeho Shin and Feiran Wang and Sen Wu and Ce Zhang},
	journal = {SIGMOD Record},
	title = {DeepDive: Declarative Knowledge Base Construction.},
	url = {http://doi.acm.org/10.1145/2949741.2949756},
	year = {2016}
}

@inproceedings{abc,
	author = {Jaeho Shin and Sen Wu and Feiran Wang and Christopher De Sa and Ce Zhang and Christopher R{\'e}},
	booktitle = {PVLDB},
	title = {Incremental Knowledge Base Construction Using DeepDive.},
	url = {http://www.vldb.org/pvldb/vol8/p1310-shin.pdf},
	year = {2015}
}

@article{abc,
	author = {Ce Zhang and Christopher R{\'e} and Amir Abbas Sadeghian and Zifei Shan and Jaeho Shin and Feiran Wang and Sen Wu},
	journal = {CoRR},
	title = {Feature Engineering for Knowledge Base Construction.},
	url = {http://arxiv.org/abs/1407.6439},
	year = {2014}
}

@inproceedings{abc,
	author = {Christopher R{\'e} and Amir Abbas Sadeghian and Zifei Shan and Jaeho Shin and Feiran Wang and Sen Wu and Ce Zhang},
	booktitle = {IEEE Data Eng. Bull.},
	title = {Feature Engineering for Knowledge Base Construction.},
	url = {http://sites.computer.org/debull/A14sept/p26.pdf},
	year = {2014}
}