论文标题

文字旅行:通过旅行推销员问题的一维单词嵌入

Word Tour: One-dimensional Word Embeddings via the Traveling Salesman Problem

论文作者

Sato, Ryoma

论文摘要

单词嵌入是自然语言处理中最基本的技术之一。现有的单词嵌入是高维的,并且消耗了大量的计算资源。在这项研究中,我们提出了文字,无监督的一维单词嵌入。为了实现具有挑战性的目标,我们提出了将单词嵌入的desiderata分解为两个部分,完整性和健全性,并专注于本文中的健全性。由于单一维度,WordTour非常有效,并且提供了处理单词嵌入的最小手段。我们通过用户研究和文档分类实验确认了该方法的有效性。

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.

扫码加入交流群

加入微信交流群

微信交流群二维码

扫码加入学术交流群,获取更多资源