Learning Distributed Representations of Texts and Entities from Knowledge Base
Learning Distributed Representations of Texts and Entities from Knowledge Base
复制标题
DOI：
10.1162/tacl_a_00069
复制
发表时间：
2017-05
影响因子：
10.9
通讯作者：
Ikuya Yamada;Hiroyuki Shindo;Hideaki Takeda;Yoshiyasu Takefuji
中科院分区：
文献类型：
--
作者：
Ikuya Yamada;Hiroyuki Shindo;Hideaki Takeda;Yoshiyasu Takefuji
我们描述了一个神经网络模型，它联合学习文本和知识库实体的分布式表示。给定知识库中的一个文本，我们训练我们提出的模型来预测与该文本相关的实体。我们的模型被设计为通用的，能够轻松地处理各种NLP任务。我们使用从维基百科提取的大量文本及其实体注释来训练模型。我们在三个重要的自然语言处理任务(即句子文本相似性、实体链接和事实类问题回答)上对该模型进行了评估，这些任务涉及无监督和有监督两种设置。因此，我们在所有这三项任务上都取得了最先进的结果。我们的代码和训练有素的模型公开可供进一步的学术研究使用。
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.