Transformers for tabular data representation: A survey of models and applications
In the last few years, the natural language processing community has witnessed advances
in neural representations of free texts with transformer-based language models (LMs). Given …
in neural representations of free texts with transformer-based language models (LMs). Given …
Large language models for tabular data: Progresses and future directions
Tables contain a significant portion of the world's structured information. The ability to
efficiently and accurately understand, process, reason about, analyze, and generate tabular …
efficiently and accurately understand, process, reason about, analyze, and generate tabular …
Is table retrieval a solved problem? exploring join-aware multi-table retrieval
Retrieving relevant tables containing the necessary information to accurately answer a given
question over tables is critical to open-domain question-answering (QA) systems. Previous …
question over tables is critical to open-domain question-answering (QA) systems. Previous …
Observatory: Characterizing embeddings of relational tables
Language models and specialized table embedding models have recently demonstrated
strong performance on many tasks over tabular data. Researchers and practitioners are …
strong performance on many tasks over tabular data. Researchers and practitioners are …
Open-WikiTable: Dataset for open domain question answering with complex reasoning over table
Despite recent interest in open domain question answering (ODQA) over tables, many
studies still rely on datasets that are not truly optimal for the task with respect to utilizing …
studies still rely on datasets that are not truly optimal for the task with respect to utilizing …
Database-Augmented Query Representation for Information Retrieval
Information retrieval models that aim to search for the documents relevant to the given query
have shown many successes, which have been applied to diverse tasks. However, the …
have shown many successes, which have been applied to diverse tasks. However, the …
Bridging the gap between text-to-SQL research and real-world applications: A unified all-in-one framework for text-to-SQL
M Han, S Park, S Kim, H Kim - Knowledge-Based Systems, 2024 - Elsevier
Existing text-to-SQL research assumes the availability of gold table when generating SQL
queries. It is possible to effectively generate complex and difficult queries by leveraging …
queries. It is possible to effectively generate complex and difficult queries by leveraging …
OpenTab: Advancing large language models as open-domain table reasoners
Large Language Models (LLMs) trained on large volumes of data excel at various natural
language tasks, but they cannot handle tasks requiring knowledge that has not been trained …
language tasks, but they cannot handle tasks requiring knowledge that has not been trained …
Rb-sql: A retrieval-based llm framework for text-to-sql
Z Wu, Z Li, J Zhang, M Li, Y Zhao, R Fang, Z He… - arxiv preprint arxiv …, 2024 - arxiv.org
Large language models (LLMs) with in-context learning have significantly improved the
performance of text-to-SQL task. Previous works generally focus on using exclusive SQL …
performance of text-to-SQL task. Previous works generally focus on using exclusive SQL …
Beyond Text-to-SQL for IoT Defense: A Comprehensive Framework for Querying and Classifying IoT Threats
R Pavlich, N Ebadi, R Tarbell, B Linares, A Tan… - arxiv preprint arxiv …, 2024 - arxiv.org
Recognizing the promise of natural language interfaces to databases, prior studies have
emphasized the development of text-to-SQL systems. While substantial progress has been …
emphasized the development of text-to-SQL systems. While substantial progress has been …