Related papers: Exploring Database Normalization Effects on SQL Ge…

A new strategy, namely the "clean numerical simulation" (CNS), was proposed (J. Computational Physics, 418:109629, 2020) to gain reliable/convergent simulations (with negligible numerical noises) of spatiotemporal chaotic systems in a long…

In computer vision and natural language processing, innovations in model architecture that increase model capacity have reliably translated into gains in performance. In stark contrast with this trend, state-of-the-art reinforcement…

Large language models (LLMs) have shown promise in table Question Answering (Table QA). However, extending these capabilities to multi-table QA remains challenging due to unreliable schema linking across complex tables. Existing methods…

The advancements of Large language models (LLMs) have provided great opportunities to text-to-SQL tasks to overcome the main challenges to understand complex domain information and complex database structures in business applications. In…

A key component of most neural network architectures is the use of normalization layers, such as Batch Normalization. Despite its common use and large utility in optimizing deep architectures, it has been challenging both to generically…

The sampling of probability distributions specified up to a normalization constant is an important problem in both machine learning and statistical mechanics. While classical stochastic sampling methods such as Markov Chain Monte Carlo…

Open-weight large language models (LLMs) have significantly advanced performance in the Natural Language to SQL (NL2SQL) task. However, their effectiveness diminishes when dealing with large database schemas, as the context length…

A significant amount of the world's knowledge is stored in relational databases. However, the ability for users to retrieve facts from a database is limited due to a lack of understanding of query languages such as SQL. We propose Seq2SQL,…

Large pre-trained models, such as Bert, GPT, and Wav2Vec, have demonstrated great potential for learning representations that are transferable to a wide variety of downstream tasks . It is difficult to obtain a large quantity of supervised…

Text-to-SQL (T2SQL) evaluation in production environments poses fundamental challenges that existing benchmarks do not address. Current evaluation methodologies whether rule-based SQL matching or schema-dependent semantic parsers assume…

Recent years have seen great success in the use of neural seq2seq models on the text-to-SQL task. However, little work has paid attention to how these models generalize to realistic unseen data, which naturally raises a question: does this…

NoSQL data stores are commonly schema-less, providing no means for globally defining or managing the schema. While this offers great flexibility in early stages of application development, developers soon can experience the heavy burden of…

Text-to-SQL is emerging as a practical interface for real world databases. The dominant paradigm for Text-to-SQL is cross-database or schema-independent, supporting application schemas unseen during training. The schema of a database…

In recent years there has been increasing interest in the field of Open-Set Recognition, which allows a classification model to identify inputs as "unknown" when it encounters an object or class not in the training set. This ability to flag…

Translating natural language to SQL for data retrieval has become more accessible thanks to code generation LLMs. But how hard is it to generate SQL code? While databases can become unbounded in complexity, the complexity of queries is…

Data normalization is an essential task when modeling a classification system. When dealing with data streams, data normalization becomes especially challenging since we may not know in advance the properties of the features, such as their…

Large Language Models have recently shown impressive capabilities in reasoning and code generation, making them promising tools for natural language interfaces to relational databases. However, existing approaches often fail to generalize…

Snowflake's Cortex AISQL is a production SQL engine that integrates native semantic operations directly into SQL. This integration allows users to write declarative queries that combine relational operations with semantic reasoning,…

Query-focused table summarization requires complex reasoning, often approached through step-by-step natural language (NL) plans. However, NL plans are inherently ambiguous and lack structure, limiting their conversion into executable…

Creating challenging tabular inference data is essential for learning complex reasoning. Prior work has mostly relied on two data generation strategies. The first is human annotation, which yields linguistically diverse data but is…