论文标题
重新考虑提取问题的目标
Rethinking the Objectives of Extractive Question Answering
论文作者
论文摘要
这项工作表明，使用独立假设的目标对跨度概率$ p（a_s，a_e）= p（a_s）p（a_s）p（a_e）p（a_e）$开始，从位置$ a_s $开始，并以位置$ a_e $结束。因此，我们提出了多种方法来直接对关节概率$ p（a_s，a_e）$进行建模。在其中，我们提出了一个复合目标，该目标是由共同概率组成的，同时仍然以独立性假设为辅助目标。我们发现，复合目标在精确匹配中始终优于或等于其他假设。此外，我们确定了由独立性假设引起的常见错误并手动检查了对应的预测，这证明了化合物目标对真实示例的影响。我们的发现通过六个数据集的三种提取性质量检查模型（Bidaf，Bert，Albert）的实验支持，我们的代码，个人结果和手动分析可在线获得。
This work demonstrates that using the objective with independence assumption for modelling the span probability $P(a_s,a_e) = P(a_s)P(a_e)$ of span starting at position $a_s$ and ending at position $a_e$ has adverse effects. Therefore we propose multiple approaches to modelling joint probability $P(a_s,a_e)$ directly. Among those, we propose a compound objective, composed from the joint probability while still keeping the objective with independence assumption as an auxiliary objective. We find that the compound objective is consistently superior or equal to other assumptions in exact match. Additionally, we identified common errors caused by the assumption of independence and manually checked the counterpart predictions, demonstrating the impact of the compound objective on the real examples. Our findings are supported via experiments with three extractive QA models (BIDAF, BERT, ALBERT) over six datasets and our code, individual results and manual analysis are available online.
