arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2308.04625cs.CLcs.AI
收藏

用于评估语义变化的句子嵌入模型比较研究

A Comparative Study of Sentence Embedding Models for Assessing Semantic Variation

University of Cincinnati(辛辛那提大学)

Deven M. Mistry, Ali A. Minai

AI总结:

本文通过分析多部文学书籍中连续句子相似度时间序列和成对相似度矩阵,在真实场景下比较多种句子嵌入方法,发现它们能推断出高度相关的语义变化模式,但存在有趣差异。

摘要:

从文体、认知和语言学的角度来看,分析书籍或转录稿等长篇真实世界文本中的语义变化模式十分有趣。这对于文本分割、文档摘要和语义新颖性检测等应用也很有用。近年来出现的多种句子嵌入向量空间方法使此类分析变得可行。然而,这也引发了一个问题:各种方法产生的语义表示本身在多大程度上是一致且有意义的。在本文中,我们通过多部文学书籍中连续句子之间的语义相似度时间序列以及成对句子相似度矩阵,比较了几种近期的句子嵌入方法。与以往使用目标任务和精心构建的数据集来比较句子嵌入方法的工作不同,我们的方法提供了对这些方法“在真实场景中”的评估。我们发现,所考虑的大多数句子嵌入方法确实能推断出给定文档中高度相关的语义相似度模式,但也表现出有趣的差异。

英文摘要:

Analyzing the pattern of semantic variation in long real-world texts such as books or transcripts is interesting from the stylistic, cognitive, and linguistic perspectives. It is also useful for applications such as text segmentation, document summarization, and detection of semantic novelty. The recent emergence of several vector-space methods for sentence embedding has made such analysis feasible. However, this raises the issue of how consistent and meaningful the semantic representations produced by various methods are in themselves. In this paper, we compare several recent sentence embedding methods via time-series of semantic similarity between successive sentences and matrices of pairwise sentence similarity for multiple books of literature. In contrast to previous work using target tasks and curated datasets to compare sentence embedding methods, our approach provides an evaluation of the methods 'in the wild'. We find that most of the sentence embedding methods considered do infer highly correlated patterns of semantic similarity in a given document, but show interesting differences.

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。

↑