# Full-Time Supervision based Bidirectional RNN for Factoid Question Answering Source: [Full-Time Supervision based Bidirectional RNN for Factoid Question Answering]() Collection index: [llms.txt]() Data updated: 2025-10-25T20:22:26.903Z Authors: Dong Xu, Wu-Jun Li Published: 2016-06-19T11:03:47.000Z ## Abstract Recently, bidirectional recurrent neural network (BRNN) has been widely used for question answering (QA) tasks with promising performance. However, most existing BRNN models extract the information of questions and answers by directly using a pooling operation to generate the representation for loss or similarity calculation. Hence, these existing models don't put supervision (loss or similarity calculation) at every time step, which will lose some useful information. In this paper, we propose a novel BRNN model called full-time supervision based BRNN (FTS-BRNN), which can put supervision at every time step. Experiments on the factoid QA task show that our FTS-BRNN can outperform other baselines to achieve the state-of-the-art accuracy. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Factoid Question Answering on Literature factoid QA (test)](): Factoid Question Answering; Literature factoid QA (test); Accuracy: 93.1. - [Factoid Question Answering on History factoid QA (test)](): Factoid Question Answering; History factoid QA (test); Accuracy: 88.1. ## Original sources and implementation [Original paper]() [PDF]()