论文标题
MS率：从潜在正确的候选人中积累证据以选择答案
MS-Ranker: Accumulating Evidence from Potentially Correct Candidates for Answer Selection
论文作者
论文摘要
由于常规的答案选择（AS）通常将问题与每个候选人的答案匹配，因此他们在问题和候选人之间缺乏匹配信息。为了解决这个问题，我们提出了一种新颖的加强学习（RL）的多步排名模型，名为MS-ranker，该模型将来自潜在正确的候选人答案中的信息积累，作为将问题与候选人匹配的额外证据。具体而言，我们明确考虑候选人的潜在正确性，并使用门控机制更新证据。此外，随着我们使用列表排名奖励，我们的模型学会了更多地关注整体性能。在两个基准测试基准（即Wikiqa和Semeval-2016 CQA）上进行的实验表明，我们的模型大大优于不依赖外部资源的现有方法。
As conventional answer selection (AS) methods generally match the question with each candidate answer independently, they suffer from the lack of matching information between the question and the candidate. To address this problem, we propose a novel reinforcement learning (RL) based multi-step ranking model, named MS-Ranker, which accumulates information from potentially correct candidate answers as extra evidence for matching the question with a candidate. In specific, we explicitly consider the potential correctness of candidates and update the evidence with a gating mechanism. Moreover, as we use a listwise ranking reward, our model learns to pay more attention to the overall performance. Experiments on two benchmarks, namely WikiQA and SemEval-2016 CQA, show that our model significantly outperforms existing methods that do not rely on external resources.
