@inproceedings{a6dbc823f4944f55bf363ac28b800658,
title = "Exploring Heterogeneous Data Lake based on Unified Canonical Graphs",
abstract = "A data lake is a repository for massive raw and heterogeneous data, which includes multiple data models with different data schemas and query interfaces. Keyword search can extract valuable information for users without the knowledge of underlying schemas and query languages. However, conventional keyword searches are restricted to a certain data model and cannot easily adapt to a data lake. In this paper, we study a novel keyword search. To achieve high accuracy and efficiency, we introduce canonical graphs and then integrate semantically related vertices based on vertex representations. A matching entity based keyword search algorithm is presented to find answers across multiple data sources. Finally, extensive experimental study shows the effectiveness and efficiency of our solution.",
keywords = "canonical graph, data lake, keyword search, matching entity",
author = "Qin Yuan and Ye Yuan and Zhenyu Wen and He Wang and Chen Chen and Guoren Wang",
note = "Publisher Copyright: {\textcopyright} 2022 ACM.; 45th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2022 ; Conference date: 11-07-2022 Through 15-07-2022",
year = "2022",
month = jul,
day = "7",
doi = "10.1145/3477495.3531759",
language = "English",
series = "SIGIR 2022 - Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval",
publisher = "Association for Computing Machinery, Inc",
pages = "1834--1838",
booktitle = "SIGIR 2022 - Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval",
}