Evaluating KGR10 Polish Word Embeddings in the recognition of temporal expressions using BiLSTM-CRF

• Autorzy: Kocoń Jan , Gawor Michał
• Języki publikacji: EN

Abstrakty

EN

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.

Słowa kluczowe

EN

word embeddings; temporal expressions; recognition; TimeML; CRF; LSTM; BiLSTM; KGR10; FastText

• Wydawca: Wydawnictwo Uniwersytetu Jagiellońskiego
• Czasopismo: Schedae Informaticae
• Rocznik: 2018
• Tom: Vol. 27

Twórcy

autor

Kocoń Jan

• Department of Computational Intelligence, Faculty of Computer Science and Management, Wroclaw University of Technology

autor

Gawor Michał

• Department of Computational Intelligence, Faculty of Computer Science and Management, Wroclaw University of Technology

Uwagi

Opracowanie rekordu w ramach umowy 509/P-DUN/2018 ze środków MNiSW przeznaczonych na działalność upowszechniającą naukę (2019).