This data contains semantic vectors from ConceptNet Numberbatch, by Luminoso Technologies, Inc. You may redistribute or modify the data under the terms of the Creative Commons Attribution-ShareAlike 4.0 license: https://creativecommons.org/licenses/by-sa/4.0/ https://creativecommons.org/licenses/by-sa/4.0/legalcode Source: https://github.com/commonsense/conceptnet-numberbatch Release: English Numberbatch 19.08 Authors: Robyn Speer, Joshua Chin, Catherine Havasi, and contributors. Citation: Speer, Chin, Havasi (2017), ConceptNet 5.5: An Open Multilingual Graph of General Knowledge. AAAI 2017, pp. 4444-4451. Changes for Guesswork by Toby Motteram, 2026-11-02: Filtered to the game's English word vocabulary, changed compound underscores to hyphens, normalized and quantized vectors to signed 8-bit components, split into 64 shards. These derived vectors and vocabulary are CC BY-SA 4.0. No scores or word-pair relationships were manually altered. See numberbatch-19.08-q8-v1/provenance.json for source checksum and checks. 2026-11-04: place-vectors-v1.json supplements the same model with supported names of places, people, bands and businesses excluded by the word-list filter. It uses the same signed 8-bit per-vector quantization and CC BY-SA 4.0 terms. Reproduce with scripts/guesswork-place-vectors.py and the original source file.