Structured query construction via knowledge graph embedding. Wang, R., Wang, M., Liu, J., Cochez, M., & Decker, S. Knowledge and Information Systems, 62(5):1819–1846, May, 2020. ![Structured query construction via knowledge graph embedding [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex 2 downloads In order to facilitate the accesses of general users to knowledge graphs, an increasing effort is being exerted to construct graph-structured queries of given natural language questions. At the core of the construction is to deduce the structure of the target query and determine the vertices/edges which constitute the query. Existing query construction methods rely on question understanding and conventional graph-based algorithms which lead to inefficient and degraded performances facing complex natural language questions over knowledge graphs with large scales. In this paper, we focus on this problem and propose a novel framework standing on recent knowledge graph embedding techniques. Our framework first encodes the underlying knowledge graph into a low-dimensional embedding space by leveraging generalized local knowledge graphs. Given a natural language question, the learned embedding representations of the knowledge graph are utilized to compute the query structure and assemble vertices/edges into the target query. Extensive experiments were conducted on the benchmark dataset, and the results demonstrate that our framework outperforms state-of-the-art baseline models regarding effectiveness and efficiency.
@article{wang_structured_2020,
title = {Structured query construction via knowledge graph embedding},
volume = {62},
issn = {0219-3116},
url = {https://doi.org/10.1007/s10115-019-01401-x},
doi = {10.1007/s10115-019-01401-x},
abstract = {In order to facilitate the accesses of general users to knowledge graphs, an increasing effort is being exerted to construct graph-structured queries of given natural language questions. At the core of the construction is to deduce the structure of the target query and determine the vertices/edges which constitute the query. Existing query construction methods rely on question understanding and conventional graph-based algorithms which lead to inefficient and degraded performances facing complex natural language questions over knowledge graphs with large scales. In this paper, we focus on this problem and propose a novel framework standing on recent knowledge graph embedding techniques. Our framework first encodes the underlying knowledge graph into a low-dimensional embedding space by leveraging generalized local knowledge graphs. Given a natural language question, the learned embedding representations of the knowledge graph are utilized to compute the query structure and assemble vertices/edges into the target query. Extensive experiments were conducted on the benchmark dataset, and the results demonstrate that our framework outperforms state-of-the-art baseline models regarding effectiveness and efficiency.},
number = {5},
journal = {Knowledge and Information Systems},
author = {Wang, Ruijie and Wang, Meng and Liu, Jun and Cochez, Michael and Decker, Stefan},
month = may,
year = {2020},
pages = {1819--1846},
}
Downloads: 2
{"_id":"ALYeQWPsxHbqwDHzP","bibbaseid":"wang-wang-liu-cochez-decker-structuredqueryconstructionviaknowledgegraphembedding-2020","author_short":["Wang, R.","Wang, M.","Liu, J.","Cochez, M.","Decker, S."],"bibdata":{"bibtype":"article","type":"article","title":"Structured query construction via knowledge graph embedding","volume":"62","issn":"0219-3116","url":"https://doi.org/10.1007/s10115-019-01401-x","doi":"10.1007/s10115-019-01401-x","abstract":"In order to facilitate the accesses of general users to knowledge graphs, an increasing effort is being exerted to construct graph-structured queries of given natural language questions. At the core of the construction is to deduce the structure of the target query and determine the vertices/edges which constitute the query. Existing query construction methods rely on question understanding and conventional graph-based algorithms which lead to inefficient and degraded performances facing complex natural language questions over knowledge graphs with large scales. In this paper, we focus on this problem and propose a novel framework standing on recent knowledge graph embedding techniques. Our framework first encodes the underlying knowledge graph into a low-dimensional embedding space by leveraging generalized local knowledge graphs. Given a natural language question, the learned embedding representations of the knowledge graph are utilized to compute the query structure and assemble vertices/edges into the target query. Extensive experiments were conducted on the benchmark dataset, and the results demonstrate that our framework outperforms state-of-the-art baseline models regarding effectiveness and efficiency.","number":"5","journal":"Knowledge and Information Systems","author":[{"propositions":[],"lastnames":["Wang"],"firstnames":["Ruijie"],"suffixes":[]},{"propositions":[],"lastnames":["Wang"],"firstnames":["Meng"],"suffixes":[]},{"propositions":[],"lastnames":["Liu"],"firstnames":["Jun"],"suffixes":[]},{"propositions":[],"lastnames":["Cochez"],"firstnames":["Michael"],"suffixes":[]},{"propositions":[],"lastnames":["Decker"],"firstnames":["Stefan"],"suffixes":[]}],"month":"May","year":"2020","pages":"1819–1846","bibtex":"@article{wang_structured_2020,\n\ttitle = {Structured query construction via knowledge graph embedding},\n\tvolume = {62},\n\tissn = {0219-3116},\n\turl = {https://doi.org/10.1007/s10115-019-01401-x},\n\tdoi = {10.1007/s10115-019-01401-x},\n\tabstract = {In order to facilitate the accesses of general users to knowledge graphs, an increasing effort is being exerted to construct graph-structured queries of given natural language questions. At the core of the construction is to deduce the structure of the target query and determine the vertices/edges which constitute the query. Existing query construction methods rely on question understanding and conventional graph-based algorithms which lead to inefficient and degraded performances facing complex natural language questions over knowledge graphs with large scales. In this paper, we focus on this problem and propose a novel framework standing on recent knowledge graph embedding techniques. Our framework first encodes the underlying knowledge graph into a low-dimensional embedding space by leveraging generalized local knowledge graphs. Given a natural language question, the learned embedding representations of the knowledge graph are utilized to compute the query structure and assemble vertices/edges into the target query. Extensive experiments were conducted on the benchmark dataset, and the results demonstrate that our framework outperforms state-of-the-art baseline models regarding effectiveness and efficiency.},\n\tnumber = {5},\n\tjournal = {Knowledge and Information Systems},\n\tauthor = {Wang, Ruijie and Wang, Meng and Liu, Jun and Cochez, Michael and Decker, Stefan},\n\tmonth = may,\n\tyear = {2020},\n\tpages = {1819--1846},\n}\n\n","author_short":["Wang, R.","Wang, M.","Liu, J.","Cochez, M.","Decker, S."],"key":"wang_structured_2020","id":"wang_structured_2020","bibbaseid":"wang-wang-liu-cochez-decker-structuredqueryconstructionviaknowledgegraphembedding-2020","role":"author","urls":{"Paper":"https://doi.org/10.1007/s10115-019-01401-x"},"metadata":{"authorlinks":{}},"downloads":2},"bibtype":"article","biburl":"https://api.zotero.org/groups/4799514/items?key=euYq5cdKpGK6xljQmpW8AeSb&format=bibtex&limit=100","dataSources":["H6xuGqu5uQ6rXhdJ4","jRiMQcLQ4TWHSS6Mc","dJmTXpbSWWjnxatYT","KenkBKiHAK4JSijXa","qyx6bB8ujfH9zqTzu"],"keywords":[],"search_terms":["structured","query","construction","via","knowledge","graph","embedding","wang","wang","liu","cochez","decker"],"title":"Structured query construction via knowledge graph embedding","year":2020,"downloads":2}