Focused Attention Improves Document-Grounded Generation -- Shrimai Prabhumoye @ NAACL 2021

Focused Attention Improves Document-Grounded Generation -- Shrimai Prabhumoye @ NAACL 2021

May 24, 2021
|
28 views
Details
Focused Attention Improves Document-Grounded Generation Shrimai Prabhumoye, Kazuma Hashimoto, Yingbo Zhou, Alan W Black, Ruslan Salakhutdinov Document grounded generation is the task of using the information provided in a document to improve text generation. This work focuses on two different document grounded generation tasks: Wikipedia Update Generation task and Dialogue response generation. Our work introduces two novel adaptations of large scale pre-trained encoder-decoder models focusing on building context driven representation of the document and enabling specific attention to the information in the document. Additionally, we provide a stronger BART baseline for these tasks. Our proposed techniques outperform existing methods on both automated (at least 48% increase in BLEU-4 points) and human evaluation for closeness to reference and relevance to the document. Furthermore, we perform comprehensive manual inspection of the generated output and categorize errors to provide insights into future directions in modeling these tasks. https://arxiv.org/abs/2104.12714 https://github.com/shrimai/Focused-Attention-Improves-Document-Grounded-Generation #NLProc #MachineLearning #NAACL2021

Comments
loading...