PixT3: Pixel-based Table To Text generation

arXiv:2311.09808v2 Announce Type: replace
Abstract: Table-to-text generation involves generating appropriate textual descriptions given structured tabular data. It has attracted increasing attention in recent years thanks to the popularity of neural network models and the availability of large-scale datasets. A common feature across existing methods is their treatment of the input as a string, i.e., by employing linearization techniques that do not always preserve information in the table, are verbose, and lack space efficiency. We propose to rethink data-to-text generation as …

abstract arxiv attention availability cs.cl data datasets feature network neural network pixel scale string table tabular tabular data text text generation textual treatment type