SECOS is an unsupervised compound splitter that uses a distributional thesaurus for learning how to split compounds.

Here we provide models for various languages computed using word2vec and JoBimText. 

The software is available under the permissive Apache license (ASL) 2.0 at github (https://github.com/riedlma/SECOS).


The tools are based on the following publication:

Martin Riedl, Chris Biemann (2016): Unsupervised Compound Splitting With Distributional Semantics Rivals Supervised Methods, In: Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2016), San Diego, CA, USA (pdf)