Vector representations of polish words (Word2Vec method)
2016
Model skip gram with vectors of length 100. Trained on kgr 10, a corpora with over 4 billion tokens. Data preprocessing involved segmentation, lemmatization and mophosyntactic disambiguation with MWE annotation.
Keywords:
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
0
References
2
Citations
NaN
KQI