KGR10 FastText Polish word embeddings

  Authors

Kocoń, Jan

 Date issued

2018-09-28

 Type

languageDescription

 Language(s)

Polish

 Description

Distributional language model (both textual and binary) for Polish (word embeddings) trained on KGR10 corpus (over 4 billion of words) using Fasttext with the following variants (all possible combinations): - dimension: 100, 300 - method: skipgram, cbow - tool: FastText, Magnitude - source text: plain, plain.lower, plain.lemma, plain.lemma.lower The link below leads to the NextCloud directory with all variants of embeddings. If you use it, please cite the following article: @article{kocon2018embeddings, author = {Koco\'{n}, Jan and Gawor, Micha{\l}}, title = {Evaluating {KGR10} {P}olish word embeddings in the recognition of temporal expressions using {BiLSTM-CRF}}, journal = {Schedae Informaticae}, volume = {27}, year = {2018}, url = {http://www.ejournals.eu/Schedae-Informaticae/2018/Volume-27/art/13931/}, doi = {10.4467/20838476SI.18.008.10413} }

 Publisher

Wroclaw University of Science and Technology

 Acknowledgement

Ministry of Science and Higher Education (Poland)

Project code: N/A

Project name: CLARIN-PL

 Subject(s)

Polish embeddings word embeddings KGR10 Fasttext skipgram cbow

 Collection(s)

CLARIN-PL

Show full item record