scholarly journals Bidirectional Long Short-Term Memory Network with a Conditional Random Field Layer for Uyghur Part-Of-Speech Tagging

Information ◽  
2017 ◽  
Vol 8 (4) ◽  
pp. 157 ◽  
Author(s):  
Maihemuti Maimaiti ◽  
Aishan Wumaier ◽  
Kahaerjiang Abiderexiti ◽  
Tuergen Yibulayin
Keyword(s):  
Random Field ◽  
Short Term Memory ◽  
Conditional Random Field ◽  
Short Term ◽  
Term Memory ◽  
Part Of Speech Tagging ◽  
Part Of Speech ◽  
Memory Network ◽  
Long Short Term Memory ◽  
Speech Tagging

scholarly journals Towards Tokenization and Part-of-Speech Tagging for Khmer: Data and Discussion

2021 ◽  
Vol 20 (6) ◽  
pp. 1-16
Author(s):  
Hour Kaing ◽  
Chenchen Ding ◽  
Masao Utiyama ◽  
Eiichiro Sumita ◽  
Sethserey Sam ◽  
...  
Keyword(s):  
Short Term Memory ◽  
Conditional Random Field ◽  
Support Vector ◽  
Part Of Speech Tagging ◽  
Pos Tagging ◽  
Part Of Speech ◽  
Long Short Term Memory ◽  
Syntactic Annotation ◽  
Near Future ◽  
Speech Tagging

As a highly analytic language, Khmer has considerable ambiguities in tokenization and part-of-speech (POS) tagging processing. This topic is investigated in this study. Specifically, a 20,000-sentence Khmer corpus with manual tokenization and POS-tagging annotation is released after a series of work over the last 4 years. This is the largest morphologically annotated Khmer dataset as of 2020, when this article was prepared. Based on the annotated data, experiments were conducted to establish a comprehensive benchmark on the automatic processing of tokenization and POS-tagging for Khmer. Specifically, a support vector machine, a conditional random field (CRF) , a long short-term memory (LSTM) -based recurrent neural network, and an integrated LSTM-CRF model have been investigated and discussed. As a primary conclusion, processing at morpheme-level is satisfactory for the provided data. However, it is intrinsically difficult to identify further grammatical constituents of compounds or phrases because of the complex analytic features of the language. Syntactic annotation and automatic parsing for Khmer will be scheduled in the near future.

scholarly journals Part-of-Speech-Based Long Short-Term Memory Network for Learning Sentence Representations

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 51810-51816 ◽  
Author(s):  
Wenhao Zhu ◽  
Tengjun Yao ◽  
Wu Zhang ◽  
Baogang Wei
Keyword(s):  
Short Term Memory ◽  
Short Term ◽  
Term Memory ◽  
Part Of Speech ◽  
Memory Network ◽  
Long Short Term Memory
Sign in / Sign up

Export Citation Format

Share Document