KAAPA: Knowledge Aware Answers from PDF Analysis
Abstract
We present KaaPa (Knowledge Aware Answers from Pdf Analysis), an integrated solution for machine reading comprehension over both text and tables extracted from PDFs. KaaPa enables interactive question refinement using facets generated from an automatically induced Knowledge Graph. In addition it provides a concise summary of the supporting evidence for the provided answers by aggregating information across multiple sources. KaaPa can be applied consistently to any collection of documents in English with zero domain adaptation effort. We showcase the use of KaaPa for QA on scientific literature using the COVID-19 Open Research Dataset.
Cite
Text
Fauceglia et al. "KAAPA: Knowledge Aware Answers from PDF Analysis." AAAI Conference on Artificial Intelligence, 2021. doi:10.1609/AAAI.V35I18.18002Markdown
[Fauceglia et al. "KAAPA: Knowledge Aware Answers from PDF Analysis." AAAI Conference on Artificial Intelligence, 2021.](https://mlanthology.org/aaai/2021/fauceglia2021aaai-kaapa/) doi:10.1609/AAAI.V35I18.18002BibTeX
@inproceedings{fauceglia2021aaai-kaapa,
title = {{KAAPA: Knowledge Aware Answers from PDF Analysis}},
author = {Fauceglia, Nicolas R. and Canim, Mustafa and Gliozzo, Alfio and Liang, Jennifer J. and Wang, Nancy Xin Ru and Burdick, Douglas and Mihindukulasooriya, Nandana and Castelli, Vittorio and Feigenblat, Guy and Konopnicki, David and Katsis, Yannis and Florian, Radu and Li, Yunyao and Roukos, Salim and Sil, Avirup},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2021},
pages = {16029-16031},
doi = {10.1609/AAAI.V35I18.18002},
url = {https://mlanthology.org/aaai/2021/fauceglia2021aaai-kaapa/}
}