arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.08433cs.CLcs.IR
收藏

词嵌入方法是否稳定,我们是否应当关注这一点?

Are Word Embedding Methods Stable and Should We Care About It?

National Institute of Technology Silchar(锡尔卡尔国家技术学院);Indian Institute of Information Technology Guwahati(古瓦哈蒂印度信息技术学院);Indian Institute of Technology Guwahati(古瓦哈蒂印度理工学院)

Angana Borah, Manash Pratim Barman, Amit Awekar

AI总结:

本文通过基于词相似度的内在评估,考察 Word2Vec、GloVe 和 fastText 在多领域数据集、训练参数及下游任务中的稳定性,发现 fastText 最稳定。

摘要:

如果一种表示学习方法能够在多次运行中持续为给定数据生成相似的表示,那么它就被认为是稳定的。词嵌入方法(WEMs)是一类表示学习方法,用于为给定文本数据中的每个词生成稠密向量表示。本文的核心思想是利用基于词相似度的内在评估来探索 WEMs 的稳定性度量。我们对三种流行的 WEM:Word2Vec、GloVe 和 fastText 进行了实验。在稳定性度量方面,我们研究了训练这些模型时涉及的五个参数的影响。我们使用来自不同领域的四个真实世界数据集开展实验:Wikipedia、News、Song lyrics 和 European parliament proceedings。我们还观察了 WEM 稳定性对三个下游任务的影响:聚类、POS 标注和公平性评估。实验表明,在三种 WEM 中,fastText 最稳定,其次是 GloVe 和 Word2Vec。

英文摘要:

A representation learning method is considered stable if it consistently generates similar representation of the given data across multiple runs. Word Embedding Methods (WEMs) are a class of representation learning methods that generate dense vector representation for each word in the given text data. The central idea of this paper is to explore the stability measurement of WEMs using intrinsic evaluation based on word similarity. We experiment with three popular WEMs: Word2Vec, GloVe, and fastText. For stability measurement, we investigate the effect of five parameters involved in training these models. We perform experiments using four real-world datasets from different domains: Wikipedia, News, Song lyrics, and European parliament proceedings. We also observe the effect of WEM stability on three downstream tasks: Clustering, POS tagging, and Fairness evaluation. Our experiments indicate that amongst the three WEMs, fastText is the most stable, followed by GloVe and Word2Vec.

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。

↑