期刊
TEXT, SPEECH, AND DIALOGUE
卷 9924, 期 -, 页码 173-181出版社
SPRINGER-VERLAG BERLIN
DOI: 10.1007/978-3-319-45510-5_20
关键词
Neural networks; Named entity recognition; Czech; Word embeddings; Character-level embeddings; Parametric rectified linear unit (PReLU); Gated linear unit (GRU)
We present a completely featureless, language agnostic named entity recognition system. Following recent advances in artificial neural network research, the recognizer employs parametric rectified linear units (PReLU), word embeddings and character-level embeddings based on gated linear units (GRU). Without any feature engineering, only with surface forms, lemmas and tags as input, the network achieves excellent results in Czech NER and surpasses the current state of the art of previously published Czech NER systems, which use manually designed rule-based orthographic classification features. Furthermore, the neural network achieves robust results even when only surface forms are available as input. In addition, the proposed neural network can use the manually designed rule-based orthographic classification features and in such combination, it exceeds the current state of the art by a wide margin.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据