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 2211.08142cs.CLcs.AIcs.LO
收藏

连续向量空间中数学表达的语义表示

Semantic Representations of Mathematical Expressions in a Continuous Vector Space

University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)

Neeraj Gangwar, Nickvash Kani

AI总结:

针对数学表达式语义表示难题,提出基于序列到序列编码器训练等价表达式对生成向量嵌入,优于结构方法,并发布等价表达式语料库。

摘要:

数学符号构成了STEM文献的很大一部分,然而为公式寻找语义表示仍然是一个具有挑战性的问题。由于数学符号精确,且其含义随微小字符变化而显著改变,适用于自然文本的方法不一定适用于数学表达式。本文描述了一种在连续向量空间中表示数学表达式的方法。我们使用序列到序列架构的编码器,该编码器在视觉上不同但数学上等价的表达式上训练,以生成向量表示(或嵌入)。我们将此方法与考虑视觉布局的结构方法进行比较,并表明我们提出的方法在捕捉数学语义方面更优。最后,为促进未来研究,我们发布了一个等价的超越和代数表达式对的语料库。

英文摘要:

Mathematical notation makes up a large portion of STEM literature, yet finding semantic representations for formulae remains a challenging problem. Because mathematical notation is precise, and its meaning changes significantly with small character shifts, the methods that work for natural text do not necessarily work well for mathematical expressions. This work describes an approach for representing mathematical expressions in a continuous vector space. We use the encoder of a sequence-to-sequence architecture, trained on visually different but mathematically equivalent expressions, to generate vector representations (or embeddings). We compare this approach with a structural approach that considers visual layout to embed an expression and show that our proposed approach is better at capturing mathematical semantics. Finally, to expedite future research, we publish a corpus of equivalent transcendental and algebraic expression pairs.

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。

↑