TY - GEN
T1 - Completion and parsing Chinese sentences using cogent confabulation
AU - Li, Zhe
AU - Qiu, Qinru
N1 - Publisher Copyright:
© 2014 IEEE.
PY - 2014/1/23
Y1 - 2014/1/23
N2 - Among different languages' sentence completion and parsing, Chinese is of great difficulty. Chinese words are not naturally separated by delimiters, which imposes extra challenge. Cogent confabulation based sentence completion has been proposed for English. It fills in missing words in an English sentence while maintains the semantic and syntactic consistency. In this work, we improve the cogent confabulation model and apply it to sentence completion in Chinese. Incorporating trained knowledge in parts-of-speech tagging and Chinese word compound segmentation, the model does not only fill missing words in a sentence but also performs linguistic analysis of the sentence with a high accuracy. We further investigate the optimization of the model and trade-offs between accuracy and training/recall complexity. Experimental results show that the optimized model improves recall accuracy by 9% and reduces training and recall time by 18.6% and 53.7% respectively.
AB - Among different languages' sentence completion and parsing, Chinese is of great difficulty. Chinese words are not naturally separated by delimiters, which imposes extra challenge. Cogent confabulation based sentence completion has been proposed for English. It fills in missing words in an English sentence while maintains the semantic and syntactic consistency. In this work, we improve the cogent confabulation model and apply it to sentence completion in Chinese. Incorporating trained knowledge in parts-of-speech tagging and Chinese word compound segmentation, the model does not only fill missing words in a sentence but also performs linguistic analysis of the sentence with a high accuracy. We further investigate the optimization of the model and trade-offs between accuracy and training/recall complexity. Experimental results show that the optimized model improves recall accuracy by 9% and reduces training and recall time by 18.6% and 53.7% respectively.
KW - Chinese sentence completion
KW - cogent confabulation
KW - mutual information
KW - parts-of-speech tagging
KW - word segmentation
UR - http://www.scopus.com/inward/record.url?scp=84988302640&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84988302640&partnerID=8YFLogxK
U2 - 10.1109/CCMB.2014.7020691
DO - 10.1109/CCMB.2014.7020691
M3 - Conference contribution
AN - SCOPUS:84988302640
T3 - IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - CCMB 2014: 2014 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain, Proceedings
SP - 31
EP - 38
BT - IEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - CCMB 2014
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2014 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain, CCMB 2014
Y2 - 9 December 2014 through 12 December 2014
ER -