Focused Attention Improves Document-Grounded Generation
Shrimai Prabhumoye, Kazuma Hashimoto, Yingbo Zhou, Alan W Black, Ruslan Salakhutdinov
Abstract
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.
BibTeX
@inproceedings{prabhumoye-etal-2021-focused,
title = "Focused Attention Improves Document-Grounded Generation",
author = "Prabhumoye, Shrimai and
Hashimoto, Kazuma and
Zhou, Yingbo and
Black, Alan W and
Salakhutdinov, Ruslan",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.338/",
doi = "10.18653/v1/2021.naacl-main.338",
pages = "4274--4287"
}