QASA: Advanced Document Retriever for Open-Domain Question Answering by Learning to Rank Question-Aware Self-Attentive Document Representations

For information consumers, being able to obtain a short and accurate answer for a query is one of the most desirable features. This motivation, along with the rise of deep learning, has led to a boom in open-domain Question Answering (QA) research. While the problem of machine comprehension has received multiple success with the help of large training corpora and the emergence of attention mechanism, the development of document retrieval in open-domain QA is lagged behind. In this work, we propose a novel encoding method for learning question-aware self-attentive document representations. By applying pair-wise ranking approach to these encodings, we build a Document Retriever, called QASA, which is then integrated with a machine reader to form a complete open-domain QA system. Our system is thoroughly evaluated using QUASAR-T dataset and shows surpassing results compared to other state-of-the-art methods.