@inproceedings{L16-1612,
 abstract = {In this paper we present SCALE, a new Python toolkit that contains two extensions to n-gram language models. The first extension is a novel technique to model compound words called Semantic Head Mapping (SHM). The second extension, Bag-of-Words Language Modeling (BagLM), bundles popular models such as Latent Semantic Analysis and Continuous Skip-grams. Both extensions scale to large data and allow the integration into first-pass ASR decoding. The toolkit is open source, includes working examples and can be found on http://github.com/jorispelemans/scale.
},
 address = {Portorož, Slovenia},
 author = {Joris Pelemans and Lyan Verwimp and Kris Demuynck and Hugo Van hamme and Patrick Wambacq},
 booktitle = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016)},
 month = {May},
 pages = {3868--3871},
 publisher = {European Language Resources Association (ELRA)},
 title = {SCALE: A Scalable Language Engineering Toolkit},
 url = {https://www.aclweb.org/anthology/L16-1612},
 year = {2016}
}