Document grounded generation is the task of using the information provided in a document to improve text generation . Our proposed techniques outperform existing methods on bothautomated (at least 48% increase in BLEU-4 points) and human evaluation for closeness to reference and relevance to the document . We performcomprehensive manual inspection of the generated output and categorize errorsto provide insights into future directions in modeling these tasks . We provide a stronger BART baselinefor these tasks. We provide an improved BART baseline for the tasks. Furthermore, we provide a better BART baseline .

Author(s) : Shrimai Prabhumoye, Kazuma Hashimoto, Yingbo Zhou, Alan W Black, Ruslan Salakhutdinov

Links : PDF - Abstract

Code :

Keywords : document - provide - bart - tasks - generation -

Leave a Reply

Your email address will not be published. Required fields are marked *