Can your encoder-decoder model generate a database-like table? We intended to do it efficiently and ended up with the STable🐴framework applicable to problems such as extraction of line items or joint entity and relation extraction.

See arxiv.org/abs/2206.04045 and 🧵
#NLProc From receipts and invoices, through paycheck stubs and insurance loss run reports, to scientific articles, real-world documents contain explicitly or implicitly tabular data to be extracted. These are not necessarily represented as a table per se within the input document.