TY - JOUR AU - Wang, Shuohang AU - Yu, Mo AU - Guo, Xiaoxiao AU - Wang, Zhiguo AU - Klinger, Tim AU - Zhang, Wei AU - Chang, Shiyu AU - Tesauro, Gerry AU - Zhou, Bowen AU - Jiang, Jing PY - 2018/04/26 Y2 - 2024/03/28 TI - R<sup>3</sup>: Reinforced Ranker-Reader for Open-Domain Question Answering JF - Proceedings of the AAAI Conference on Artificial Intelligence JA - AAAI VL - 32 IS - 1 SE - Main Track: NLP and Text Mining DO - 10.1609/aaai.v32i1.12053 UR - https://ojs.aaai.org/index.php/AAAI/article/view/12053 SP - AB - <p> In recent years researchers have achieved considerable success applying neural network methods to question answering (QA). These approaches have achieved state of the art results in simplified closed-domain settings such as the SQuAD (Rajpurkar et al. 2016) dataset, which provides a pre-selected passage, from which the answer to a given question may be extracted. More recently, researchers have begun to tackle open-domain QA, in which the model is given a question and access to a large corpus (e.g., wikipedia) instead of a pre-selected passage (Chen et al. 2017a). This setting is more complex as it requires large-scale search for relevant passages by an information retrieval component, combined with a reading comprehension model that “reads” the passages to generate an answer to the question. Performance in this setting lags well behind closed-domain performance. In this paper, we present a novel open-domain QA system called Reinforced Ranker-Reader (R<sup>3</sup>), based on two algorithmic innovations. First, we propose a new pipeline for open-domain QA with a Ranker component, which learns to rank retrieved passages in terms of likelihood of extracting the ground-truth answer to a given question. Second, we propose a novel method that jointly trains the Ranker along with an answer-extraction Reader model, based on reinforcement learning. We report extensive experimental results showing that our method significantly improves on the state of the art for multiple open-domain QA datasets. </p> ER -