Papers with Code · CC BY-SA 4.0

Chinese Word Segmentation

Chinese › Chinese Word Segmentation 21 평가 기록 6 datasets

Chinese word segmentation is the task of splitting Chinese text (i.e. a sequence of Chinese characters) into words (Source: www.nlpprogress.com).

논문

Unsupervised Boundary-Aware Language Model Pretraining for Chinese Sequence Labeling

2210.15231 2022-10-27 이 페이지의 평가 8건

F1: 97.56

Improving Chinese Word Segmentation with Wordhood Memory Networks

2020-07-01 이 페이지의 평가 5건

F1: 97.93

Glyce: Glyph-vectors for Chinese Character Representations

1901.10125 2019-01-29 이 페이지의 평가 4건

F1: 97.9Precision: 97.9Recall: 98

ZEN: Pre-training Chinese Text Encoder Enhanced by N-gram Representations

1911.00720 2019-11-02 이 페이지의 평가 2건

F1: 98.35

LATTE: Lattice ATTentive Encoding for Character-based Word Segmentation

2023-06-01 이 페이지의 평가 1건

F1: 98.07

Long Short-Term Memory Neural Networks for Chinese Word Segmentation

2015-09-01 이 페이지의 평가 1건

F1: 97.4