- Remove
data/ngram_probs.jsonfrom the gem - Eager load model in Rails
- Use binary model format: Reduce memory by searching a packed binary model instead of parsing JSON into hashes. Slower throughput though.
- Train bundled model from German Wiktionary nouns (~95% head-detection accuracy on GermaNet compounds)
- Add Ruby training pipeline (
bin/train.rb) and third-party notices
- Initial release