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

TL;DR

WordTour introduces a novel, efficient one-dimensional word embedding method based on the Traveling Salesman Problem, focusing on soundness, and validated through user studies and document classification.

Contribution

It proposes a new one-dimensional embedding approach using TSP decomposition, emphasizing soundness, and demonstrates its efficiency and effectiveness.

Findings

WordTour is highly efficient due to its single-dimensional nature.

The method shows promising results in user studies.

Document classification performance is improved with WordTour.

Abstract

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.