arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.07196cs.CLcs.NE
收藏

现有词嵌入方法的综合实证评估

A Comprehensive Empirical Evaluation of Existing Word Embedding Approaches

South Asian University(南亚大学)

Obaidullah Zaland, Muhammad Abulaish, Mohd. Fazil

AI总结:

本文对现有词嵌入方法进行综合实证评估,将传统矩阵分解方法与基于神经网络的方法分类比较,并通过多个分类任务揭示各自更具优势的应用场景。

摘要:

基于向量的词表示有助于众多自然语言处理(NLP)任务捕捉语言的语义和句法规律。本文介绍了现有词嵌入方法的特征,并针对许多分类任务对其进行分析。我们将这些方法分为两大类:传统方法主要使用矩阵分解来生成词表示,无法很好地捕捉语言的语义和句法规律;另一方面,基于神经网络的方法能够捕捉语言的复杂规律,并在生成的词表示中保留词与词之间的关系。我们报告了在多个分类任务上的实验结果,并重点说明了某一种方法相较其他方法表现更好的场景。

英文摘要:

Vector-based word representations help countless Natural Language Processing (NLP) tasks capture the language's semantic and syntactic regularities. In this paper, we present the characteristics of existing word embedding approaches and analyze them with regard to many classification tasks. We categorize the methods into two main groups - Traditional approaches mostly use matrix factorization to produce word representations, and they are not able to capture the semantic and syntactic regularities of the language very well. On the other hand, Neural-network-based approaches can capture sophisticated regularities of the language and preserve the word relationships in the generated word representations. We report experimental results on multiple classification tasks and highlight the scenarios where one approach performs better than the rest.

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。

↑