arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1705.02494cs.CLcs.NE
收藏

从知识库中学习文本和实体的分布式表示

Learning Distributed Representations of Texts and Entities from Knowledge Base

Studio Ousia;Nara Institute of Science and Technology(奈良先端科学技术大学院大学);National Institute of Informatics(国立情报学研究所);Keio University(庆应义塾大学)

Ikuya Yamada, Hiroyuki Shindo, Hideaki Takeda, Yoshiyasu Takefuji

摘要:

我们描述了一个神经网络模型,共同学习分布式表示的文本和知识库(KB)的实体。给定知识库中的文本,我们训练我们提出的模型来预测与文本相关的实体。我们的模型被设计为通用的,能够轻松地解决各种NLP任务。我们训练模型使用一个大型语料库的文本和他们的实体注释提取自维基百科。我们在三个重要的NLP任务(即,句子文本相似性、实体链接和仿真问答),涉及无监督和监督设置。因此,我们在这三项任务上都取得了最先进的成果。我们的代码和训练模型可供进一步的学术研究公开使用。

英文摘要:

We describe a neural network model that jointly learns distributed representations of texts and knowledge base (KB) entities. Given a text in the KB, we train our proposed model to predict entities that are relevant to the text. Our model is designed to be generic with the ability to address various NLP tasks with ease. We train the model using a large corpus of texts and their entity annotations extracted from Wikipedia. We evaluated the model on three important NLP tasks (i.e., sentence textual similarity, entity linking, and factoid question answering) involving both unsupervised and supervised settings. As a result, we achieved state-of-the-art results on all three of these tasks. Our code and trained models are publicly available for further academic research.

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。

↑