GAAMA 2.0: An Integrated System that Answers Boolean and Extractive Questions

TL;DR

GAAMA 2.0 is a multilingual machine reading comprehension system that effectively answers both boolean and extractive questions, providing evidence highlighting and achieving top leaderboard rankings.

Contribution

The paper introduces an integrated system capable of handling both boolean and extractive questions within a single framework, with two implementation variants for efficiency.

Findings

Ranked first on the Tydi QA leaderboard.

Two implementation approaches demonstrated effectiveness.

System supports multilingual question answering.

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 multilingual machine reading comprehension system and front-end demo that handles boolean questions by providing both a YES/NO answer and highlighting supporting evidence, and handles extractive questions by highlighting the answer in the passage. Our system, GAAMA 2.0, is ranked first on the Tydi QA leaderboard at the time of this writing. We contrast two different implementations of our approach. The first includes several independent stacks of transformers allowing easy deployment of each component. The second is a single stack of transformers utilizing adapters to reduce GPU memory footprint in a resource-constrained environment.