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

arXiv: https://arxiv.org/abs/2206.08441 · HTML: https://mlsanity.com/paper/2206.08441/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 25 references that are in the map.
- First posted on arXiv 16 Jun 2022.

## Builds on (most cited first, 18 of 18)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [AdapterFusion: Non-Destructive Task Composition for Transfer Learning](https://mlsanity.com/paper/2005.00247/) (2020)
- [TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages](https://mlsanity.com/paper/2003.05002/) (2020)
- [MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer](https://mlsanity.com/paper/2005.00052/) (2020)
- [AdapterHub: A Framework for Adapting Transformers](https://mlsanity.com/paper/2007.07779/) (2020)
- [End-to-End Open-Domain Question Answering with BERTserini](https://mlsanity.com/paper/1902.01718/) (2019)
- [Poolingformer: Long Document Modeling with Pooling Attention](https://mlsanity.com/paper/2105.04371/) (2021)
- [A BERT Baseline for the Natural Questions](https://mlsanity.com/paper/1901.08634/) (2019)
- [Document Modeling with Graph Attention Networks for Multi-grained Machine Reading Comprehension](https://mlsanity.com/paper/2005.05806/) (2020)
- [Talk to Papers: Bringing Neural Question Answering to Academic Search](https://mlsanity.com/paper/2004.02002/) (2020)
- [Do Answers to Boolean Questions Need Explanations? Yes](https://mlsanity.com/paper/2112.07772/) (2021)
- [Improved Synthetic Training for Reading Comprehension](https://mlsanity.com/paper/2010.12776/) (2020)
- [CFO: A Framework for Building Production NLP Systems](https://mlsanity.com/paper/1908.06121/) (2019)

## Built on by (most cited first, 1 of 1)

- [PrimeQA: The Prime Repository for State-of-the-Art Multilingual Question Answering Research and Development](https://mlsanity.com/paper/2301.09715/) (2023)

## Abstract (arXiv)

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.