gTBLS: Generating Tables from Text by Conditional Question Answering

arXiv:2403.14457v1 Announce Type: cross
Abstract: Distilling large, unstructured text into a structured, condensed form such as tables is an open research problem. One of the primary challenges in automatically generating tables is ensuring their syntactic validity. Prior approaches address this challenge by including additional parameters in the Transformer's attention mechanism to attend to specific rows and column headers. In contrast to this single-stage method, this paper presents a two-stage approach called Generative Tables (gTBLS). The first stage infers table structure …

abstract arxiv attention challenge challenges cs.cl cs.ir cs.lg form parameters prior question question answering research tables text transformer type unstructured