MetaQA: Combining Expert Agents for Multi-Skill Question Answering
Puerto H, Şahin GG, Gurevych I (2023)
Publication Type: Conference contribution
Publication year: 2023
Publisher: Association for Computational Linguistics (ACL)
Pages Range: 3548-3562
Conference Proceedings Title: EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference
Event location: Dubrovnik, Croatia, HRV
ISBN: 9781959429449
DOI: 10.18653/v1/2023.eacl-main.259
Abstract
The recent explosion of question-answering (QA) datasets and models has increased the interest in the generalization of models across multiple domains and formats by either training on multiple datasets or combining multiple models. Despite the promising results of multi-dataset models, some domains or QA formats may require specific architectures, and thus the adaptability of these models might be limited. In addition, current approaches for combining models disregard cues such as question-answer compatibility. In this work, we propose to combine expert agents with a novel, flexible, and training-efficient architecture that considers questions, answer predictions, and answer-prediction confidence scores to select the best answer among a list of answer predictions. Through quantitative and qualitative experiments, we show that our model i) creates a collaboration between agents that outperforms previous multi-agent and multi-dataset approaches, ii) is highly data-efficient to train, and iii) can be adapted to any QA format. We release our code and a dataset of answer predictions from expert agents for 16 QA datasets to foster future research of multi-agent systems.
Involved external institutions
Germany (DE)
Turkey (TR)How to cite
APA:
Puerto, H., Şahin, G.G., & Gurevych, I. (2023). MetaQA: Combining Expert Agents for Multi-Skill Question Answering. In EACL 2023 - 17th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference (pp. 3548-3562). Dubrovnik, Croatia, HRV: Association for Computational Linguistics (ACL).
MLA:
Puerto, Haritz, Gözde Gül Şahin, and Iryna Gurevych. "MetaQA: Combining Expert Agents for Multi-Skill Question Answering." Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2023, Dubrovnik, Croatia, HRV Association for Computational Linguistics (ACL), 2023. 3548-3562.
BibTeX: Download