Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userBERT Meets Relational DB: Contextual Representations of Relational Databases
130
0
0.0
(
0
)
Added by
Garima Gaur
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
In this paper, we address the problem of learning low dimension representation of entities on relational databases consisting of multiple tables. Embeddings help to capture semantics encoded in the database and can be used in a variety of settings like auto-completion of tables, fully-neural query processing of relational joins queries, seamlessly handling missing values, and more. Current work is restricted to working with just single table, or using pretrained embeddings over an external corpus making them unsuitable for use in real-world databases. In this work, we look into ways of using these attention-based model to learn embeddings for entities in the relational database. We are inspired by BERT style pretraining methods and are interested in observing how they can be extended for representation learning on structured databases. We evaluate our approach of the autocompletion of relational databases and achieve improvement over standard baselines.
rate research
Read More
One of the distinctive features of Information Retrieval systems comparing to Database Management systems, is that they offer better compression for posting lists, resulting in better I/O performance and thus faster query evaluation. In this paper, we introduce database representations of the index that reduce the size (and thus the disk I/Os) of the posting lists. This is not achieved by redesigning the DBMS, but by exploiting the non 1NF features that existing Object-Relational DBM systems (ORDBMS) already offer. Specifically, four different database representations are described and detailed experimental results for one million pages are reported. Three of these representations are one order of magnitude more space efficient and faster (in query evaluation) than the plain relational representation.
Lenses are a popular approach to bidirectional transformations, a generalisation of the view update problem in databases, in which we wish to make changes to source tables to effect a desired change on a view. However, perhaps surprisingly, lenses have seldom actually been used to implement updatable views in databases. Bohannon, Pierce and Vaughan proposed an approach to updatable views called relational lenses, but to the best of our knowledge this proposal has not been implemented or evaluated to date. We propose incremental relational lenses, that equip relational lenses with change-propagating semantics that map small changes to the view to (potentially) small changes to the source tables. We also present a language-integrated implementation of relational lenses and a detailed experimental evaluation, showing orders of magnitude improvement over the non-incremental approach. Our work shows that relational lenses can be used to support expressive and efficient view updates at the language level, without relying on updatable view support from the underlying database.
We propose a novel data augmentation method for labeled sentences called conditional BERT contextual augmentation. Data augmentation methods are often applied to prevent overfitting and improve generalization of deep neural network models. Recently proposed contextual augmentation augments labeled sentences by randomly replacing words with more varied substitutions predicted by language model. BERT demonstrates that a deep bidirectional language model is more powerful than either an unidirectional language model or the shallow concatenation of a forward and backward model. We retrofit BERT to conditional BERT by introducing a new conditional masked language modelfootnote{The term conditional masked language model appeared once in original BERT paper, which indicates context-conditional, is equivalent to term masked language model. In our paper, conditional masked language model indicates we apply extra label-conditional constraint to the masked language model.} task. The well trained conditional BERT can be applied to enhance contextual augmentation. Experiments on six various different text classification tasks show that our method can be easily applied to both convolutional or recurrent neural networks classifier to obtain obvious improvement.
Embedding-based methods for reasoning in knowledge hypergraphs learn a representation for each entity and relation. Current methods do not capture the procedural rules underlying the relations in the graph. We propose a simple embedding-based model called ReAlE that performs link prediction in knowledge hypergraphs (generalized knowledge graphs) and can represent high-level abstractions in terms of relational algebra operations. We show theoretically that ReAlE is fully expressive and provide proofs and empirical evidence that it can represent a large subset of the primitive relational algebra operations, namely renaming, projection, set union, selection, and set difference. We also verify experimentally that ReAlE outperforms state-of-the-art models in knowledge hypergraph completion, and in representing each of these primitive relational algebra operations. For the latter experiment, we generate a synthetic knowledge hypergraph, for which we design an algorithm based on the Erdos-Renyi model for generating random graphs.
Variability inherently exists in databases in various contexts which creates database variants. For example, variants of a database could have different schemas/content (database evolution problem), variants of a database could root from different sources (data integration problem), variants of a database could be deployed differently for specific application domain (deploying a database for different configurations of a software system), etc. Unfortunately, while there are specific solutions to each of the problems arising in these contexts, there is no general solution that accounts for variability in databases and addresses managing variability within a database. In this paper, we formally define variational databases (VDBs) and statically-typed variational relational algebra (VRA) to query VDBs---both database and queries explicitly account for variation. We also design and implement variational database management system (VDBMS) to run variational queries over a VDB effectively and efficiently. To assess this, we generate two VDBs from real-world databases in the context of software development and database evolution with a set of experimental queries for each.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
