Tables are powerful and popular tools for organizing and manipulating data. A vast number
of tables can be found on the Web, which represent a valuable knowledge resource. The …

Since a vast number of tables can be easily collected from web pages, spreadsheets, PDFs,
and various other document types, a flurry of table pre-training frameworks have been …

Relational tables on the Web store a vast amount of knowledge. Owing to the wealth of such
tables, there has been tremendous progress on a variety of tasks in the area of table …

Existing work on tabular representation learning jointly models tables and associated text
using self-supervised objective functions derived from pretrained language models such as …

We propose TUTA, a unified pre-training architecture for understanding generally structured
tables. Noticing that understanding a table requires spatial, hierarchical, and semantic …

Tables are information-rich structured objects in document images. While significant work
has been done in localizing tables as graphic objects in document images, only limited …

We present GraPPa, an effective pre-training approach for table semantic parsing that learns
a compositional inductive bias in the joint representations of textual and tabular data. We …

Tabular data are ubiquitous for the widespread applications of tables and hence have
attracted the attention of researchers to extract underlying information. One of the critical …

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 …

Transcribing structured data into natural language descriptions has emerged as a
challenging task, referred to as “data-to-text”. These structures generally regroup multiple …