首页> 外文会议>Natural language understanding and intelligent applications >An Open Domain Topic Prediction Model for Answer Selection
【24h】

An Open Domain Topic Prediction Model for Answer Selection

机译:用于答案选择的开放域主题预测模型

获取原文
获取原文并翻译 | 示例

摘要

We present an open domain topic prediction model for the answer selection task. Different from previous unsupervised topic modeling methods, we automatically extract high quality and large scale (sentence, topic) pairs from Wikipedia as labeled data, and train an open domain topic prediction model based on convolutional neural network, which can predict the most possible topics for each given input sentence. To verify the usefulness of our proposed approach, we add the topic prediction model into an end-to-end open domain question answering system and evaluate it on the answer selection task, and improvements are obtained on both WikiQA and QASent datasets.
机译:我们为答案选择任务提供了一个开放域主题预测模型。与以前的无监督主题建模方法不同,我们自动从Wikipedia中提取高质量和大规模(句子,主题)对作为标记数据,并基于卷积神经网络训练一个开放域主题预测模型,该模型可以预测最可能的主题每个给定的输入句子。为了验证我们提出的方法的有效性,我们将主题预测模型添加到端到端的开放域问答系统中,并在答案选择任务上对其进行了评估,并且在WikiQA和QASent数据集上均获得了改进。

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