Word Tour: One-dimensional Word Embeddings via the Traveling Salesman Problem
Word Tour: One-dimensional Word Embeddings via the Traveling Salesman Problem
复制标题
DOI：
10.48550/arxiv.2205.01954
复制
发表时间：
2022-05
期刊：
影响因子：
--
通讯作者：
R. Sato
中科院分区：
文献类型：
--
作者：
R. Sato
词嵌入是自然语言处理中最基本的技术之一。现有的词嵌入是高维的，消耗大量的计算资源。在这项研究中，我们提出了WordTour，无监督的一维词嵌入。为了实现这一具有挑战性的目标，我们提出了一个分解的desiderata的词嵌入为两个部分，完整性和可靠性，并专注于可靠性在本文中。由于单维性，WordTour非常高效，并提供了一种最小的方法来处理单词嵌入。我们通过用户学习和文档分类实验证实了所提出的方法的有效性。
Word embeddings are one of the most fundamental technologies used in natural language processing. Existing word embeddings are high-dimensional and consume considerable computational resources. In this study, we propose WordTour, unsupervised one-dimensional word embeddings. To achieve the challenging goal, we propose a decomposition of the desiderata of word embeddings into two parts, completeness and soundness, and focus on soundness in this paper. Owing to the single dimensionality, WordTour is extremely efficient and provides a minimal means to handle word embeddings. We experimentally confirmed the effectiveness of the proposed method via user study and document classification.