GAAMA 2.0: An Integrated System That Answers Boolean and Extractive Questions
Scott McCarley, Mihaela Bornea, Sara Rosenthal, Anthony Ferritto, Md Arafat Sultan, Avirup Sil, Radu Florian
Abstract
Recent machine reading comprehension datasets include extractive and boolean questions but current approaches do not offer integrated support for answering both question types. We present a front-end demo to a multilingual machine reading comprehension system that handles boolean and extractive questions. It provides a yes/no answer and highlights the supporting evidence for boolean questions. It provides an answer for extractive questions and highlights the answer in the passage. Our system, GAAMA 2.0, achieved first place on the TyDi QA leaderboard at the time of submission. We contrast two different implementations of our approach: including multiple transformer models for easy deployment, and a shared transformer model utilizing adapters to reduce GPU memory footprint for a resource-constrained environment.
BibTeX
@article{McCarley_Bornea_Rosenthal_Ferritto_Sultan_Sil_Florian_2024, title={GAAMA 2.0: An Integrated System That Answers Boolean and Extractive Questions}, volume={37}, url={https://ojs.aaai.org/index.php/AAAI/article/view/27079}, DOI={10.1609/aaai.v37i13.27079}, abstractNote={Recent machine reading comprehension datasets include extractive and boolean questions but current approaches do not offer integrated support for answering both question types. We present a front-end demo to a multilingual machine reading comprehension system that handles boolean and extractive questions. It provides a yes/no answer and highlights the supporting evidence for boolean questions. It provides an answer for extractive questions and highlights the answer in the passage. Our system, GAAMA 2.0, achieved first place on the TyDi QA leaderboard at the time of submission. We contrast two different implementations of our approach: including multiple transformer models for easy deployment, and a shared transformer model utilizing adapters to reduce GPU memory footprint for a resource-constrained environment.}, number={13}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={McCarley, Scott and Bornea, Mihaela and Rosenthal, Sara and Ferritto, Anthony and Sultan, Md Arafat and Sil, Avirup and Florian, Radu}, year={2024}, month={Jul.}, pages={16461-16463} }