SRQA: Synthetic Reader for Factoid Question Answering

TL;DR

SRQA introduces a multi-evidence question answering model that improves evidence representation, reasoning, and robustness through multilayer attention, cross evidence strategy, and adversarial training, achieving state-of-the-art results.

Contribution

The paper presents SRQA, a novel model combining multilayer attention, cross evidence reasoning, and adversarial training for enhanced factoid question answering across multiple evidences.

Findings

Outperforms state-of-the-art models on WebQA dataset.

Achieves a fuzzy score of up to 78.56%.

Demonstrates improved reasoning and noise robustness.

Abstract

The question answering system can answer questions from various fields and forms with deep neural networks, but it still lacks effective ways when facing multiple evidences. We introduce a new model called SRQA, which means Synthetic Reader for Factoid Question Answering. This model enhances the question answering system in the multi-document scenario from three aspects: model structure, optimization goal, and training method, corresponding to Multilayer Attention (MA), Cross Evidence (CE), and Adversarial Training (AT) respectively. First, we propose a multilayer attention network to obtain a better representation of the evidences. The multilayer attention mechanism conducts interaction between the question and the passage within each layer, making the token representation of evidences in each layer takes the requirement of the question into account. Second, we design a cross evidence strategy to choose the answer span within more evidences. We improve the optimization goal, considering all the answers' locations in multiple evidences as training targets, which leads the model to reason among multiple evidences. Third, adversarial training is employed to high-level variables besides the word embedding in our model. A new normalization method is also proposed for adversarial perturbations so that we can jointly add perturbations to several target variables. As an effective regularization method, adversarial training enhances the model's ability to process noisy data. Combining these three strategies, we enhance the contextual representation and locating ability of our model, which could synthetically extract the answer span from several evidences. We perform SRQA on the WebQA dataset, and experiments show that our model outperforms the state-of-the-art models (the best fuzzy score of our model is up to 78.56%, with an improvement of about 2%).