安利一下我同学的一篇paper，分析了一下几个在CNN/DM/CBT上面比较好的几个模型attention sum/gated attention sum/stanford reader其实本质是差不多的。然后stanford reader虽然在这个数据集上效果很好但是一旦数据集不anonymize就很容易不work了。

　　WDW dataset:Passage: 直接给一个例子。

　　Britain’s decision on Thursday to drop extradition proceedings against Gen. Augusto Pinochet and allow him to return to Chile is understandably frustrating … Jack Straw, the home secretary, said the 84-year-old former dictator’s ability to understand the charges against him and to direct his defense had been seriously impaired by a series of strokes. … Chile’s president-elect, Ricardo Lagos, has wisely pledged to let justice run its course. But the outgoing government of President Eduardo Frei is pushing a constitutional reform that would allow Pinochet to step down from the Senate and retain parliamentary immunity from prosecution. …

　　Question: Sources close to the presidential palace said that Fujimori declined at the last moment to leave the country and instead he will send a high level delegation to the ceremony, at which Chilean President Eduardo Frei will pass the mandate to XXX.

　　Choices: (1) Augusto Pinochet (2) Jack Straw (3) Ricardo Lagos

　　还有一个dataset叫wiki QA我也没有在上面实验过，也给一个例子。

　　Question: Who wrote second Corinthians? Second Epistle to the Corinthians The Second Epistle to the Corinthians, often referred to as Second Corinthians (and written as 2 Corinthians), is the eighth book of the New Testament of the Bible. Paul the Apostle and “Timothy our brother” wrote this epistle to “the church of God which is at Corinth, with all the saints which are in all Achaia”.

　　个人觉得open domain以及需要external knowledge的QA DATASET其实很难，但是很重要，因为可以应用在其他更多的方面。

　　另外提一个LAMBADA dataset，虽然他的问题是last word prediction，不过我们发现用reading comprehension models也可以做出很好的效果。详细信息可以看我的一篇paper。

　　facebook有个babi dataset，

　　需要一些logical thinking，facebook自己搞了一些memory network的模型在上面效果比较好，但是其实我觉得memory network和attention模型非常相似。

　　至于本文构建的squad dataset主要的特点就是答案可能比较长，而且不给候选答案，所以难度应该会大一些 数据集的质量也比较高，因为都是人工出的问题和标准答案，数据量也很大，容易训练处有用的模型。

　　个人认为构建大的，有意义的数据集对于QA的工作是很关键的。现在还是比较缺乏能够推广到实际生活中的问题的QA模型。

　　我大致就分享这一些。给想做QA方面问题的同学一点参考。

　　活动预告

　　下一期Paper Note+Chat活动将会继续分享和解读3篇2016年最值得读的自然语言处理领域paper，分别是：

　　1.LightRNN Memory and Computation-Efficient Recurrent Neural Network

　　2.Text understanding with the attention sum reader network

　　3.Neural Machine Translation with Reconstruction

　　为保证讨论的质量，在讨论之前要求各位同学至少读过其中的一篇paper。

　　活动报名请扫码

　　关于PaperWeekly

　　PaperWeekly是一个分享知识和交流学问的学术组织，关注的领域是NLP的各个方向。如果你也经常读paper，也喜欢分享知识，也喜欢和大家一起讨论和学习的话，请速速来加入我们吧。

　　微信公众号：PaperWeekly

　　微博账号：PaperWeekly（）

　　微信交流群：微信+ zhangjun168305（请备注：加群交流或参与写paper note）