arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1606.04582cs.CLcs.NE
收藏

用于问答的查询缩减网络

Query-Reduction Networks for Question Answering

University of Washington(华盛顿大学);Seoul National University(首尔大学);Allen Institute for Artificial Intelligence(艾伦人工智能研究所)

Minjoon Seo, Sewon Min, Ali Farhadi, Hannaneh Hajishirzi

摘要:

本文研究了需要对多个事实进行推理的问答问题。我们提出了查询简化网络(QRN),它是递归神经网络(RNN)的一种变体,可以有效地处理短期(局部)和长期(全局)的顺序依赖关系,以推理多个事实。QRN认为上下文语句作为一个序列的状态变化的触发器,并减少了原来的查询,更明智的查询,因为它观察每个触发器(上下文语句)通过时间。我们的实验表明,QRN产生的最先进的结果在bAbI QA和对话任务,并在一个真正的面向目标的对话数据集。此外,QRN公式允许在RNN的时间轴上并行化,从而在训练和推理的时间复杂度上节省一个数量级。

英文摘要:

In this paper, we study the problem of question answering when reasoning over multiple facts is required. We propose Query-Reduction Network (QRN), a variant of Recurrent Neural Network (RNN) that effectively handles both short-term (local) and long-term (global) sequential dependencies to reason over multiple facts. QRN considers the context sentences as a sequence of state-changing triggers, and reduces the original query to a more informed query as it observes each trigger (context sentence) through time. Our experiments show that QRN produces the state-of-the-art results in bAbI QA and dialog tasks, and in a real goal-oriented dialog dataset. In addition, QRN formulation allows parallelization on RNN's time axis, saving an order of magnitude in time complexity for training and inference.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑