joisino/wordtour

Code for "Word Tour: One-dimensional Word Embeddings via the Traveling Salesman Problem" (NAACL 2022)

38
/ 100
Emerging

This project helps you understand how words relate to each other by arranging them into a single, continuous sequence. You provide a list of words, and it outputs a linear ordering where similar words are placed close together, revealing smooth transitions between concepts. This is useful for linguists, data scientists, or anyone analyzing text data to find relationships and patterns in language.

111 stars. No commits in the last 6 months.

Use this if you need to visualize semantic relationships between words in an intuitive, one-dimensional continuum, or if you want to improve text classification accuracy by representing words in a more semantically ordered way.

Not ideal if you require multi-dimensional word relationships or don't need a sequential ordering of words for your specific text analysis tasks.

natural-language-processing computational-linguistics text-analysis semantic-embedding information-retrieval
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

111

Forks

9

Language

Python

License

MIT

Last pushed

May 14, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/joisino/wordtour"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.