TY - JOUR
TI - Evaluating KGR10 Polish Word Embeddings in the Recognition of Temporal Expressions Using BiLSTM-CRF
AU - Kocoń, Jan
AU - Gawor, Michał
TI - Evaluating KGR10 Polish Word Embeddings in the Recognition of Temporal Expressions Using BiLSTM-CRF
AB - 
	The article introduces a new set of Polish word embeddings, built using KGR10 corpus, which contains more than 4 billion words. These embeddings are evaluated in the problem of recognition of temporal expressions (timexes) for the Polish language. We described the process of KGR10 corpus creation and a new approach to the recognition problem using Bidirectional Long-Short Term Memory (BiLSTM) network with additional CRF layer, where specific embeddings are essential. We presented experiments and conclusions drawn from them.
VL - 2018
IS - Volume 27
PY - 2018
SN - 1732-3916
C1 - 2083-8476
SP - 93
EP - 106
DO - 10.4467/20838476SI.18.008.10413
UR - https://ejournals.eu/en/journal/schedae-informaticae/article/evaluating-kgr10-polish-word-embeddings-in-the-recognition-of-temporal-expressions-using-bilstm-crf
KW - word embeddings
KW - temporal expressions
KW - recognition
KW - TimeML
KW - CRF
KW - LSTM
KW - BiLSTM
KW - KGR10
KW - FastText