Filters








21,223 Hits in 5.5 sec

Using Word Embedding to Enable Semantic Queries in Relational Databases

Rajesh Bordawekar, Oded Shmueli
2017 Proceedings of the 1st Workshop on Data Management for End-to-End Machine Learning - DEEM'17  
Relations are texti ed and the text is used to build a Word Embedding (WE) model that captures the latent relationships between database tokens of various data types.  ...  The vectors are used in the existing SQL query infrastructure via UDFs.  ...  CONTROLLED DISCLOSURE VIA WORD EMBEDDING We now outline interesting implications of using word embedding models for querying relational databases.  ... 
doi:10.1145/3076246.3076251 dblp:conf/sigmod/BordawekarS17 fatcat:o2ljou52kzf4naminuaqduatga

Cognitive Database: A Step towards Endowing Relational Databases with Artificial Intelligence Capabilities [article]

Rajesh Bordawekar and Bortik Bandyopadhyay and Oded Shmueli
2017 arXiv   pre-print
CI queries use the model vectors to enable complex queries such as semantic matching, inductive reasoning queries such as analogies, predictive queries using entities not present in a database, and, more  ...  We seamlessly integrate the word embedding model into existing SQL query infrastructure and use it to enable a new class of SQL-based analytics queries called cognitive intelligence (CI) queries.  ...  CONCLUSIONS AND SUCCESS CRITE-RIA In this paper we presented Cognitive Database, an innovative relational database system that uses the power of word embedding models to enable novel AI capabilities in  ... 
arXiv:1712.07199v1 fatcat:ltwgviux6rhmplja5xeqekxoj4

Enabling Cognitive Intelligence Queries in Relational Databases using Low-dimensional Word Embeddings [article]

Rajesh Bordawekar, Oded Shmueli
2016 arXiv   pre-print
We apply distributed language embedding methods from Natural Language Processing to assign a vector to each database entity associated token (for example, a token may be a word occurring in a table row  ...  The vectors can be used to algebraically quantify semantic relationships between the tokens such as similarities and analogies.  ...  The similarity results are then used to guide the relational query execution, thus enabling the relational engine to exploit latent semantic information for answering relational queries.  ... 
arXiv:1603.07185v1 fatcat:i4zpg7z5hjcljoujduuj3asl4e

Improving Semantic Queries by Utilizing UNL Ontology and a Graph Database

Petri Kivikangas, Mitsuru Ishizuka
2012 2012 IEEE Sixth International Conference on Semantic Computing  
This paper describes an approach for improving semantic queries by utilizing Universal Words (UWs) and a graph database.  ...  Concept Description Language (CDL) is used for representing the semantic data, and Neo4j graph database is used as the storage back-end.  ...  Enable deep semantic processing, in addition to shallow conceptual level processing 3.  ... 
doi:10.1109/icsc.2012.50 dblp:conf/semco/KivikangasI12 fatcat:55ufunhluffvtgchqu3zz6cxx4

Deep Visual-Semantic Quantization for Efficient Image Retrieval

Yue Cao, Mingsheng Long, Jianmin Wang, Shichen Liu
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
The main contribution lies in jointly learning deep visual-semantic embeddings and visual-semantic quantizers using carefullydesigned hybrid networks and well-specified loss functions.  ...  We propose Deep Visual-Semantic Quantization (DVSQ), which is the first approach to learning deep quantization models from labeled image data as well as the semantic information underlying general text  ...  The model learns to represent each word as a fixed-length embedding vector by predicting adjacent words in the document to give similar embedding vectors for semantically related words.  ... 
doi:10.1109/cvpr.2017.104 dblp:conf/cvpr/CaoL0L17 fatcat:jgzhlmcoeraqblejcdeoeovh6i

Unlocking New York City Crime Insights using Relational Database Embeddings [article]

Apoorva Nitsure and Rajesh Bordawekar and Jose Neves
2020 arXiv   pre-print
We demonstrate that AI-DB's database embedding model and semantic queries enable users to identify criminal complaint patterns that are not possible to extract using current crime analysis tools, including  ...  AI-DB uses an unsupervised neural network, db2Vec, to capture inter and intra-column semantic relationships from a relational table and allows users to exploit such relationships using novel semantic SQL  ...  Inductive Reasoning Queries A unique feature of embedding models such as word and database embeddings is their capability to answer inductive reasoning queries that enable an individual to reason from  ... 
arXiv:2005.09617v2 fatcat:jbodmk6dsrdjhpywgwet75cd2e

TechNet: Technology Semantic Network Based on Patent Data

Serhad Sarica, Jianxi Luo, Kristin L. Wood
2019 Expert systems with applications  
The growing developments in general semantic networks, knowledge graphs and ontology databases have motivated us to build a large-scale comprehensive semantic network of technology-related data for engineering  ...  To derive the TechNet, natural language processing techniques were utilized to extract terms from massive patent texts and recent word embedding algorithms were employed to vectorize such terms and establish  ...  The semantic relations also enable query prediction and expansion to make technology-related searches or knowledge discovery more intelligent.  ... 
doi:10.1016/j.eswa.2019.112995 fatcat:mrc6a2ujynezzd2hk2t5zs6xvi

Searching databases for sematically-related schemas

Gauri Shah, Tanveer Syeda-Mahmood
2004 Proceedings of the 27th annual international conference on Research and development in information retrieval - SIGIR '04  
In this paper, we address the problem of searching schema databases for semantically-related schemas.  ...  Matching schemas in the database are found by hashing the query attributes and recording peaks in the histogram of schema hits.  ...  Conclusions In this paper, we have presented an approach to search for semantically related schemas in the database, in response to queries.  ... 
doi:10.1145/1008992.1009092 dblp:conf/sigir/ShahS04 fatcat:j76kojx2cbhdva5gtbe34ypcp4

Learning a Compositional Semantics for Freebase with an Open Predicate Vocabulary

Jayant Krishnamurthy, Tom M. Mitchell
2015 Transactions of the Association for Computational Linguistics  
We also compare our approach against manually annotated Freebase queries, finding that our open predicate vocabulary enables us to answer many questions that Freebase cannot.  ...  Crucially, our approach uses an open predicate vocabulary, enabling it to produce denotations for phrases such as "Republican front-runner from Texas" whose semantics cannot be represented using the Freebase  ...  Acknowledgments This research was supported in part by DARPA under contract number FA8750-13-2-0005, and by a generous grant from Google.  ... 
doi:10.1162/tacl_a_00137 fatcat:vuoo5747drfkdmjaa344kdli6q

Vec2SPARQL: integrating SPARQL queries and knowledge graph embeddings

Maxat Kulmanov, Şenay Kafkas, Andreas Karwath, Alexander Malic, Georgios V Gkoutos, Michel Dumontier, Robert Hoehndorf
2018 Figshare  
The featuresare represented as vectors and may encode for some semantic aspects of data.They can be used in a machine learning models for different tasks or to com-pute similarities between the entities  ...  SPARQL is a query languagefor structured data originally developed for querying Resource Description Frame-work (RDF) data. It has been in use for over a decade as a standardized NoSQLquery language.  ...  For example, analogical reasoning can be performed using addition and subtraction based on word embeddings generated by Word2Vec [24] , and in translational embedding models it is possible to add relation  ... 
doi:10.6084/m9.figshare.7356416.v2 fatcat:iqvn3jbotzhc3ne4wfchrqfh4q

Semantic Web Framework for Development of Very Large Ontologies

Sergey Yablonsky
2009 POLIBITS Research Journal on Computer Science and Computer Engineering With Applications  
Application of lexical ontologies such as WordNet and others for different tasks on the Semantic Web requires their representation in RDF and/or OWL formats with possibility of the different ontology mappings  ...  , semantic workflows, services and other semantic technologies.  ...  Querying of RDF/OWL data and ontologies using SPARQL-like graph patterns embedded in SQL Ontology-assisted querying of enterprise (relational) data storage Loading, and DML access to semantic data Based  ... 
doi:10.17562/pb-39-3 fatcat:cm2yqzkvkjglbc6f7gvtrxbxfu

Khmer Word Search: Challenges, Solutions, and Semantic-Aware Search [article]

Rina Buoy and Nguonly Taing and Sovisal Chenda
2021 arXiv   pre-print
Moreover, due to the absence of WordNet-like lexical databases for Khmer language, it is impossible to establish semantic relation between words, enabling semantic search.  ...  The semantic model is based on the word embedding model that is trained on a 30-million-word corpus and is used to capture the semantic similarities between words.  ...  បំែលង , the search is unable to find any possible to establish semantic relation be- match since បែម្លង and បំែលង are treated tween words, enabling semantic search.  ... 
arXiv:2112.08918v1 fatcat:65v4dmwdjnghfmjy4qwcvp2xke

Carbon to Diamond: An Incident Remediation Assistant System From Site Reliability Engineers' Conversations in Hybrid Cloud Operations [article]

Suranjana Samanta, Ajay Gupta, Prateeti Mohapatra, Amar Prakash Azad
2020 arXiv   pre-print
This makes it difficult to use the standard natural language processing frameworks directly, which are popularly used in standard NLP tasks.  ...  In this paper, we build a framework that taps into the conversational channels and uses various learning methods to (a) understand and extract key artefacts from conversations like diagnostic steps and  ...  We train FastText embedding model on documents collected from the hybrid cloud domain, which enables us to learn the domain-specific terms and the relations between them in an effective way.  ... 
arXiv:2010.05569v1 fatcat:wdohx4hmt5hbjisv3iou3ujvca

Recent Advances in SQL Query Generation: A Survey [article]

Jovan Kalajdjieski, Martina Toshevska, Frosina Stojanovska
2020 arXiv   pre-print
Providing natural language interface to relational databases could possibly attract a vast majority of users that are or are not proficient with query languages.  ...  With the rise of deep learning techniques, there is extensive ongoing research in designing a suitable natural language interface to relational databases.  ...  This language is the main query language for relational databases currently in use.  ... 
arXiv:2005.07667v1 fatcat:ilxq5lc4yvfz7lmtb5kedtrdzy

Vec2SPARQL: integrating SPARQL queries and knowledge graph embeddings [article]

Maxat Kulmanov, Senay Kafkas, Andreas Karwath, Alexander Malic, Georgios V Gkoutos, Michel Dumontier, Robert Hoehndorf
2018 biorxiv/medrxiv   pre-print
It has been in use for over a decade as a standardized NoSQL query language. Many different tools have been developed to enable data sharing with SPARQL.  ...  They can be used in a machine learning models for different tasks or to compute similarities between the entities of the data.  ...  For example, analogical reasoning can be performed using addition and subtraction based on word embeddings generated by Word2Vec [24] , and in translational embedding models it is possible to add relation  ... 
doi:10.1101/463778 fatcat:x3qi6swk3jedhevqdpza7cayq4
« Previous Showing results 1 — 15 out of 21,223 results