• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Annual meeting of the Association for Computational Linguistics >Simple and Effective Curriculum Pointer-Generator Networks for Reading Comprehension over Long Narratives
【24h】

Simple and Effective Curriculum Pointer-Generator Networks for Reading Comprehension over Long Narratives

机译：简单有效的课程指针-生成器网络，用于阅读长篇小说

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

This paper tackles the problem of reading comprehension over long narratives where documents easily span over thousands of tokens. We propose a curriculum learning (CL) based Pointer-Generator framework for reading/sampling over large documents, enabling diverse training of the neural model based on the notion of alternating contextual difficulty. This can be interpreted as a form of domain randomization and/or generative pre-training during training. To this end, the usage of the Pointer-Generator softens the requirement of having the answer within the context, enabling us to construct diverse training samples for learning. Additionally, we propose a new Introspective Alignment Layer (IAL), which reasons over decomposed alignments using block-based self-attention. We evaluate our proposed method on the NarrativeQA reading comprehension benchmark, achieving state-of-the-art performance, improving existing baselines by 51% relative improvement on BLEU-4 and 17% relative improvement on Rouge-L. Extensive ablations confirm the effectiveness of our proposed IAL and CL components.
机译：本文解决了对冗长叙事的阅读理解问题，在这种叙事中文档很容易跨越成千上万个标记。我们提出了一种基于课程学习（CL）的Pointer-Generator框架，用于在大型文档上进行读取/采样，从而能够基于交替的上下文难度概念对神经模型进行多种训练。这可以解释为训练期间域随机化和/或生成式预训练的一种形式。为此，使用Pointer-Generator可以减轻在上下文中具有答案的要求，从而使我们能够构建用于学习的各种训练样本。此外，我们提出了一个新的自省式比对层（IAL），这是使用基于块的自注意力导致比对分解的原因。我们在NarrativeQA阅读理解基准上评估了我们提出的方法，实现了最先进的性能，将现有基准线的BLEU-4相对改善了51％，将Rouge-L相对改善了17％。广泛的消融证实了我们建议的IAL和CL组件的有效性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号