Related papers: OptiSQL: Executable SQL Generation from Optical To…
Transforming natural language into SQL queries (NL2SQL) is crucial for data-driven business applications. Existing frameworks, trained on open-source datasets, struggle with complex business logic and lack domain-specific data for…
Semantic ID learning is a key interface in Generative Recommendation (GR) models, mapping items to discrete identifiers grounded in side information, most commonly via a pretrained text encoder. However, these text encoders are primarily…
A central challenge in science is to understand how systems behaviors emerge from complex networks. This often requires aggregating, reusing, and integrating heterogeneous information. Supplementary spreadsheets to articles are a key data…
Generating structural query language (SQL) queries from natural language is a long-standing open problem. Answering a natural language question about a database table requires modeling complex interactions between the columns of the table…
Text-to-SQL semantic parsing faces challenges in generalizing to cross-domain and complex queries. Recent research has employed a question decomposition strategy to enhance the parsing of complex SQL queries. However, this strategy…
Synthetic data offers a promising solution to two persistent barriers in supply chain analytics: data scarcity and data privacy. However, for synthetic data to support operational simulation and decision-making, it must do more than…
SQL-to-Text generation aims at translating structured SQL queries into natural language descriptions, thereby facilitating comprehension of complex database operations for non-technical users. Although large language models (LLMs) have…
Operational semantics has established itself as a flexible but rigorous means to describe the meaning of programming languages. Oftentimes, it is felt necessary to keep a semantics small, for example to facilitate its use for model checking…
The conversion of natural language into SQL language for querying databases (Text-to-SQL) has broad application prospects and has attracted widespread attention. At present, the mainstream Text-to-SQL methods are mainly divided into…
Symbolic execution is a technique which enables automatically generating test inputs (and outputs) exercising a set of execution paths within a program to be tested. If the paths cover a sufficient part of the code under test, the test data…
We introduce UniToken, an auto-regressive generation model that encodes visual inputs through a combination of discrete and continuous representations, enabling seamless integration of unified visual understanding and image generation…
The text-to-SQL task is an active challenge in Natural Language Processing. Many existing solutions focus on using black-box language models extended with specialized components within customized end-to-end text-to-SQL pipelines. While…
This paper proposes a scalable and straightforward pre-training paradigm for efficient visual conceptual representation called occluded image contrastive learning (OCL). Our OCL approach is simple: we randomly mask patches to generate…
Deep code generation is a topic of deep learning for software engineering (DL4SE), which adopts neural models to generate code for the intended functions. Since end-to-end neural methods lack domain knowledge and software hierarchy…
Evaluating Text-to-SQL agents in private business intelligence (BI) settings is challenging due to the scarcity of realistic, domain-specific data. While synthetic evaluation data offers a scalable solution, existing generation methods fail…
A lot of sensor network applications are data-driven. We believe that query is the most preferred way to discover sensor services. Normally users are unaware of available sensors. Thus users need to pose different types of query over the…
Research in Text-to-SQL conversion has been largely benchmarked against datasets where each text query corresponds to one correct SQL. However, natural language queries over real-life databases frequently involve significant ambiguity about…
We present an approach to rapidly and easily build natural language interfaces to databases for new domains, whose performance improves over time based on user feedback, and requires minimal intervention. To achieve this, we adapt neural…
We present an end-to-end trainable approach for Optical Character Recognition (OCR) on printed documents. Specifically, we propose a model that predicts a) a two-dimensional character grid (\emph{chargrid}) representation of a document…
Large language models (LLMs) have advanced Text-to-SQL, yet existing solutions still fall short of system-level reliability. The limitation is not merely in individual modules -- e.g., schema linking, reasoning, and verification -- but more…