Training a Ranking Function for Open-Domain Question Answering
This addresses the challenge of improving retrieval for open-domain QA systems, which is an incremental advancement over existing machine reading methods.
The paper tackles the problem of poor performance in open-domain question answering due to difficulty in retrieving relevant passages, by proposing two neural network rankers to score passages based on their likelihood of containing the answer, and analyzes the importance of semantic similarity and word-level relevance matching.
In recent years, there have been amazing advances in deep learning methods for machine reading. In machine reading, the machine reader has to extract the answer from the given ground truth paragraph. Recently, the state-of-the-art machine reading models achieve human level performance in SQuAD which is a reading comprehension-style question answering (QA) task. The success of machine reading has inspired researchers to combine information retrieval with machine reading to tackle open-domain QA. However, these systems perform poorly compared to reading comprehension-style QA because it is difficult to retrieve the pieces of paragraphs that contain the answer to the question. In this study, we propose two neural network rankers that assign scores to different passages based on their likelihood of containing the answer to a given question. Additionally, we analyze the relative importance of semantic similarity and word level relevance matching in open-domain QA.