AI systems that serve natural language questions over databases promise to unlock tremendous value. Such systems would allow users to leverage the powerful reasoning and knowledge capabilities of language models (LMs) alongside the scalable computational power of data management systems. These combined capabilities would empower users to ask arbitrary natural language questions over custom data sources. However, existing methods and benchmarks insufficiently explore this setting. Text2SQL methods focus solely on natural language questions that can be expressed in relational algebra, representing a small subset of the questions real users wish to ask. Likewise, Retrieval-Augmented Generation (RAG) considers the limited subset of queries that can be answered with point lookups to one or a few data records within the database. We propose Table-Augmented Generation (TAG), a unified and general-purpose paradigm for answering natural language questions over databases. The TAG model represents a wide range of interactions between the LM and database that have been previously unexplored and creates exciting research opportunities for leveraging the world knowledge and reasoning capabilities of LMs over data. We systematically develop benchmarks to study the TAG problem and find that standard methods answer no more than 20% of queries correctly, confirming the need for further research in this area. We release code for the benchmark at https://github.com/TAG-Research/TAG-Bench.
In this work we establish and point out connections between the notion of query-answer causality in databases and database repairs, model-based diagnosis in its consistency-based and abductive versions, and database updates through views. The mutual relationships among these areas of data management and knowledge representation shed light on each of them and help to share notions and results they have in common. In one way or another, these are all approaches to uncertainty management, which becomes even more relevant in the context of big data that have to be made sense of.
TIGeR: Unifying Text-to-Image Generation and Retrieval with Large Multimodal Models
National University of Singapore（新加坡国立大学）；Nanyang Technological University（南洋理工大学）；University of Science and Technology of China（中国科学技术大学）；Hong Kong Polytechnic University（香港理工大学）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））
Despite their relatively low sampling factor, the freely available, randomly sampled status streams of Twitter are very useful sources of geographically embedded social network data. To statistically analyze the information Twitter provides via these streams, we have collected a year's worth of data and built a multi-terabyte relational database from it. The database is designed for fast data loading and to support a wide range of studies focusing on the statistics and geographic features of social networks, as well as on the linguistic analysis of tweets. In this paper we present the method o…
NoSQL databases support semi-structured data, typically modeled as JSON. They also provide limited (but expanding) query languages. Their idiomatic, non-SQL language constructs, the many variations, and the lack of formal semantics inhibit deep understanding of the query languages, and also impede progress towards clean, powerful, declarative query languages. This paper specifies the syntax and semantics of SQL++, which is applicable to both JSON native stores and SQL databases. The SQL++ semi-structured data model is a superset of both JSON and the SQL data model. SQL++ offers powerful comput…
Translating Natural Language Queries (NLQs) to Structured Query Language (SQL) in interfaces deployed in relational databases is a challenging task, which has been widely studied in database community recently. Conventional rule based systems utilize series of solutions as a pipeline to deal with each step of this task, namely stop word filtering, tokenization, stemming/lemmatization, parsing, tagging, and translation. Recent works have mostly focused on the translation step overlooking the earlier steps by using ad-hoc solutions. In the pipeline, one of the most critical and challenging probl…
University of California, Los Angeles（加利福尼亚大学洛杉矶分校）
We propose unifying techniques from probabilistic databases and relational embedding models with the goal of performing complex queries on incomplete and uncertain data. We formalize a probabilistic database model with respect to which all queries are done. This allows us to leverage the rich literature of theory and algorithms from probabilistic databases for solving problems. While this formalization can be used with any relational embedding model, the lack of a well-defined joint probability distribution causes simple query problems to become provably hard. With this in mind, we introduce \…
In this paper we propose a logic-based, framework inspired by artificial intelligence, but scaled down for practical database and programming applications. Computation in the framework is viewed as the task of generating a sequence of state transitions, with the purpose of making an agent's goals all true. States are represented by sets of atomic sentences (or facts), representing the values of program variables, tuples in a coordination language, facts in relational databases, or Herbrand models. In the model-theoretic semantics, the entire sequence of states and events are combined into a si…
OsmT: Bridging OpenStreetMap Queries and Natural Language with Open-source Tag-aware Language Models
The Hong Kong Polytechnic University（香港理工大学）；WeBank；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（深圳先进技术研究院，中国科学院）；The Hong Kong University of Science and Technology（香港科技大学）
The design and implementation of two software systems introduced to improve the efficiency of offline analysis of event data taken with the ZEUS Detector at the HERA electron-proton collider at DESY are presented. Two different approaches were made, one using a set of event directories and the other using a tag database based on a commercial object-oriented database management system. These are described and compared. Both systems provide quick direct access to individual collision events in a sequential data store of several terabytes, and they both considerably improve the event analysis eff…
As data lakes become increasingly popular in large enterprises today, there is a growing need to tag or classify data assets (e.g., files and databases) in data lakes with additional metadata (e.g., semantic column-types), as the inferred metadata can enable a range of downstream applications like data governance (e.g., GDPR compliance), and dataset search. Given the sheer size of today's enterprise data lakes with petabytes of data and millions of data assets, it is imperative that data assets can be ``auto-tagged'', using lightweight inference algorithms and minimal user input. In this work,…
In this paper we present a new family of Intensional RDBs (IRDBs) which extends the traditional RDBs with the Big Data and flexible and 'Open schema' features, able to preserve the user-defined relational database schemas and all preexisting user's applications containing the SQL statements for a deployment of such a relational data. The standard RDB data is parsed into an internal vector key/value relation, so that we obtain a column representation of data used in Big Data applications, covering the key/value and column-based Big Data applications as well, into a unifying RDB framework. We de…
As the rate of data collection continues to grow rapidly, developing visualization tools that scale to immense data sets is a serious and ever-increasing challenge. Existing approaches generally seek to decouple storage and visualization systems, performing just-in-time data reduction to transparently avoid overloading the visualizer. We present a new architecture in which the visualizer and data store are tightly coupled. Unlike systems that read raw data from storage, the performance of our system scales linearly with the size of the final visualization, essentially independent of the size o…
Amazon Neptune is a graph database service that supports two graph (meta)models: W3C's Resource Description Framework (RDF) and Labeled Property Graphs (LPG). Customers opt in for one or the other model, and this choice determines which data modeling features can be used, and - perhaps more importantly - which query languages are available to query and manipulate the graph. The choice between the two technology stacks is difficult and requires consideration of data modeling aspects, query language features, their adequacy for current and future use cases, as well as many other factors (includi…
Provenance is information about the origin, derivation, ownership, or history of an object. It has recently been studied extensively in scientific databases and other settings due to its importance in helping scientists judge data validity, quality and integrity. However, most models of provenance have been stated as ad hoc definitions motivated by informal concepts such as "comes from", "influences", "produces", or "depends on". These models lack clear formalizations describing in what sense the definitions capture these intuitive concepts. This makes it difficult to compare approaches, evalu…
Georgia Institute of Technology（佐治亚理工学院）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；University of California, San Diego（加州大学圣地亚哥分校）
The data revolution is fueled by advances in machine learning, databases, and hardware design. Programmable accelerators are making their way into each of these areas independently. As such, there is a void of solutions that enables hardware acceleration at the intersection of these disjoint fields. This paper sets out to be the initial step towards a unifying solution for in-Database Acceleration of Advanced Analytics (DAnA). Deploying specialized hardware, such as FPGAs, for in-database analytics currently requires hand-designing the hardware and manually routing the data. Instead, DAnA auto…
Implementing even a conceptually simple web application requires an inordinate amount of time. FORWARD addresses three problems that reduce developer productivity: (a) Impedance mismatch across the multiple languages used at different tiers of the application architecture. (b) Distributed data access across the multiple data sources of the application (SQL database, user input of the browser page, session data in the application server, etc). (c) Asynchronous, incremental modification of the pages, as performed by Ajax actions. FORWARD belongs to a novel family of web application frameworks th…
