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 models on multiple datasets or by combining multiple models. We argue that 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 candidates. 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 in both in-domain and out-of-domain scenarios, ii) is extremely data-efficient to train, and iii) can be adapted to any QA format.
Abstract (translated)
URL
https://arxiv.org/abs/2112.01922