Papers › R³: Reinforced Reader-Ranker for Open-Domain Question Answering

R³: Reinforced Reader-Ranker for Open-Domain Question Answering

31 Aug 2017arXiv:1709.00023archive 2025-07-28

Shuohang Wang, Mo Yu, Xiaoxiao Guo, Zhiguo Wang, Tim Klinger, Wei zhang, Shiyu Chang, Gerald Tesauro, Bo-Wen Zhou, Jing Jiang

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 considerably behind closed-domain performance. In this paper, we present a novel open-domain QA system called Reinforced Ranker-Reader (R³), 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 generating the ground-truth answer to a given question. Second, we propose a novel method that jointly trains the Ranker along with an answer-generation 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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

shuohangwang/mprc officialmentioned in papermentioned on GitHubtorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Answer GenerationInformation RetrievalOpen-Domain Question AnsweringQuestion AnsweringReading ComprehensionReinforcement LearningRetrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Open-Domain Question Answering Quasar R^3 EM (Quasar-T) 35.3 #4 of 6 Archive leaderboard report
Open-Domain Question Answering Quasar R^3 F1 (Quasar-T) 41.7 #4 of 6 Archive leaderboard report
Open-Domain Question Answering SearchQA R^3 EM 49.0 #8 of 14 Archive leaderboard report
Open-Domain Question Answering SearchQA R^3 F1 55.3 #8 of 14 Archive leaderboard report
Open-Domain Question Answering SearchQA R^3 N-gram F1 - #8 of 14 Archive leaderboard report
Open-Domain Question Answering SearchQA R^3 Unigram Acc - #8 of 14 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections