MLB

AbstractNeural table-to-text models, which select and order salient data, as well as verbalizing them fluently via surface realization, have achieved promising progress. Based on results from previous work, the performance …...

AbstractRecent approaches to data-to-text generation have adopted the very successful encoder-decoder architecture or variants thereof. These models generate text that is fluent (but often imprecise) and perform quite poorly at …...

AbstractWe consider the task of data-to-text generation, which aims to create textual output from non-linguistic input. We focus on generating long-form text, that is, documents with multiple paragraphs, and propose …...