arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1709.09749cs.CLcs.LGcs.NE
收藏

KeyVec:保持关键语义的文档表示

KeyVec: Key-semantics Preserving Document Representations

Microsoft Research(微软研究院)

Bin Bi, Hao Ma

摘要:

先前的研究已经证明了词嵌入在各种应用中的经验成功。在本文中,我们研究的问题,学习分布式表示的文本文件,许多机器学习算法作为输入的一些NLP任务。我们提出了一个神经网络模型,KeyVec,学习文档表示的目标是保持输入文本的关键语义。它使学习到的低维向量能够保留来自文档的主题和重要信息,这些主题和信息将流向下游任务。我们的实证评估表明,在两个不同的文档理解任务的KeyVec表示的优良品质。

英文摘要:

Previous studies have demonstrated the empirical success of word embeddings in various applications. In this paper, we investigate the problem of learning distributed representations for text documents which many machine learning algorithms take as input for a number of NLP tasks. We propose a neural network model, KeyVec, which learns document representations with the goal of preserving key semantics of the input text. It enables the learned low-dimensional vectors to retain the topics and important information from the documents that will flow to downstream tasks. Our empirical evaluations show the superior quality of KeyVec representations in two different document understanding tasks.

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。

↑