arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2109.07230cs.CLcs.LG
收藏

学习整数的数学性质

Learning Mathematical Properties of Integers

Language Technologies Institute(语言技术研究所);Carnegie Mellon University(卡内基梅隆大学);DiDi Labs(滴滴实验室)

Maria Ryskina, Kevin Knight

摘要:

在高维向量空间中嵌入词在许多自然语言应用中已被证明是有价值的。在这项工作中,我们研究了类似训练的整数嵌入是否可以捕获对数学应用有用的概念。我们探索数学知识的整数嵌入,将它们应用于一组数值推理任务,并表明通过学习数学序列数据的表示,我们可以大大提高从英语文本语料库中学习到的数字嵌入。

英文摘要:

Embedding words in high-dimensional vector spaces has proven valuable in many natural language applications. In this work, we investigate whether similarly-trained embeddings of integers can capture concepts that are useful for mathematical applications. We probe the integer embeddings for mathematical knowledge, apply them to a set of numerical reasoning tasks, and show that by learning the representations from mathematical sequence data, we can substantially improve over number embeddings learned from English text corpora.

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。

↑