KAAPA: Knowledge Aware Answers from PDF Analysis

Authors

  • Nicolas Fauceglia IBM Research AI
  • Mustafa Canim IBM Research AI
  • Alfio Gliozzo IBM Research AI
  • Jennifer J Liang IBM Research AI
  • Nancy Xin Ru Wang IBM Research AI
  • Douglas Burdick IBM Research AI
  • Nandana Mihindukulasooriya IBM Research AI
  • Vittorio Castelli IBM Research AI
  • Guy Feigenblat IBM Research AI
  • David Konopnicki IBM Research AI
  • Yannis Katsis IBM Research AI
  • Radu Florian IBM Research AI
  • Yunyao Li IBM Research AI
  • Salim Roukos IBM Research AI
  • Avirup Sil IBM Research AI

Keywords:

Question Answering, Table QA, Machine Reading Comprehension

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.

Downloads

Published

2021-05-18

How to Cite

Fauceglia, N., Canim, M., Gliozzo, A., Liang, J. J., Wang, N. X. R., Burdick, D., Mihindukulasooriya, N., Castelli, V., Feigenblat, G., Konopnicki, D., Katsis, Y., Florian, R., Li, Y., Roukos, S., & Sil, A. (2021). KAAPA: Knowledge Aware Answers from PDF Analysis. Proceedings of the AAAI Conference on Artificial Intelligence, 35(18), 16029-16031. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/18002