Related papers: FORTAP: Using Formulas for Numerical-Reasoning-Awa…

Tabular data are fundamental in common machine learning applications, ranging from finance to genomics and healthcare. This paper focuses on tabular regression tasks, a field where deep learning (DL) methods are not consistently superior to…

This paper presents TableQuery, a novel tool for querying tabular data using deep learning models pre-trained to answer questions on free text. Existing deep learning methods for question answering on tabular data have various limitations,…

Tabular data is frequently captured in image form across a wide range of real-world scenarios such as financial reports, handwritten records, and document scans. These visual representations pose unique challenges for machine understanding,…

Recent advances in tabular question answering (QA) with large language models are constrained in their coverage and only answer questions over a single table. However, real-world queries are complex in nature, often over multiple tables in…

In the realm of natural language processing, the understanding of tabular data has perpetually stood as a focal point of scholarly inquiry. The emergence of expansive language models, exemplified by the likes of ChatGPT, has ushered in a…

Comparative reasoning is a process of comparing objects, concepts, or entities to draw conclusions, which constitutes a fundamental cognitive ability. In this paper, we propose a novel framework to pre-train language models for enhancing…

Tables provide valuable knowledge that can be used to verify textual statements. While a number of works have considered table-based fact verification, direct alignments of tabular data with tokens in textual statements are rarely…

Table Question-Answering involves both understanding the natural language query and grounding it in the context of the input table to extract the relevant information. In this context, many methods have highlighted the benefits of…

Tabular data is arguably one of the most commonly used data structures in various practical domains, including finance, healthcare and e-commerce. The inherent heterogeneity allows tabular data to store rich information. However, based on a…

Tabletop exercises are used to train personnel in the efficient mitigation and resolution of incidents. They are applied in practice to support the preparedness of organizations and to highlight inefficient processes. Since tabletop…

Classical machine learning models, such as linear models and tree-based models, are widely used in industry. These models are sensitive to data distribution, thus feature preprocessing, which transforms features from one distribution to…

The use of numerical uncertainty representations allows better modeling of some aspects of human evidential reasoning. It also makes knowledge acquisition and system development, test, and modification more difficult. We propose that where…

We propose RoTaR, a row-based table representation learning method, to address the efficiency and scalability issues faced by existing table representation learning methods. The key idea of RoTaR is to generate query-agnostic row…

The risks of spreadsheet use do not just come from the misuse of formulae. As such, training needs to go beyond this technical aspect of spreadsheet use and look at the spreadsheet in its full business context. While standard training is by…

Tabular data pervades the landscape of the World Wide Web, playing a foundational role in the digital architecture that underpins online information. Given the recent influence of large-scale pretrained models like ChatGPT and SAM across…

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 on previously. One solution is to use a retriever that fetches…

Deep learning has achieved impressive performance in many domains, such as computer vision and natural language processing, but its advantage over classical shallow methods on tabular datasets remains questionable. It is especially…

Tables, typically two-dimensional and structured to store large amounts of data, are essential in daily activities like database queries, spreadsheet manipulations, web table question answering, and image table information extraction.…

While pre-trained language models have obtained state-of-the-art performance for several natural language understanding tasks, they are quite opaque in terms of their decision-making process. While some recent works focus on rationalizing…

Tabular data is prevalent across diverse domains in machine learning. With the rapid progress of deep tabular prediction methods, especially pretrained (foundation) models, there is a growing need to evaluate these methods systematically…