The development of text messaging in cell phones has influenced punctuation variations in written language. In order to determine how text messaging has resulted in paradigm shift in the traditional uses of punctuatio...The development of text messaging in cell phones has influenced punctuation variations in written language. In order to determine how text messaging has resulted in paradigm shift in the traditional uses of punctuation marks, this paper explores how punctuation marks vary with language, location, register and time, and how they are constantly evolving. The discussion in this paper is structured around Coupland＇s sociolinguistic theory. The findings reveal that new technology has impacted on the traditional uses of punctuation marks. Thus, the results show that the use of punctuation markers in Short Message Service （SMS） texts is complex. Moreover, the use of punctuation marks in Kenyan text messages reveals personal stylistic choices. However, it is apparent that Kenyan text messages are shaped by social variables.展开更多
To improve the accuracy of short text matching,a short text matching method with knowledge and structure enhancement for BERT(KS-BERT)was proposed in this study.This method first introduced external knowledge to the i...To improve the accuracy of short text matching,a short text matching method with knowledge and structure enhancement for BERT(KS-BERT)was proposed in this study.This method first introduced external knowledge to the input text,and then sent the expanded text to both the context encoder BERT and the structure encoder GAT to capture the contextual relationship features and structural features of the input text.Finally,the match was determined based on the fusion result of the two features.Experiment results based on the public datasets BQ_corpus and LCQMC showed that KS-BERT outperforms advanced models such as ERNIE 2.0.This Study showed that knowledge enhancement and structure enhancement are two effective ways to improve BERT in short text matching.In BQ_corpus,ACC was improved by 0.2%and 0.3%,respectively,while in LCQMC,ACC was improved by 0.4%and 0.9%,respectively.展开更多
文摘The development of text messaging in cell phones has influenced punctuation variations in written language. In order to determine how text messaging has resulted in paradigm shift in the traditional uses of punctuation marks, this paper explores how punctuation marks vary with language, location, register and time, and how they are constantly evolving. The discussion in this paper is structured around Coupland＇s sociolinguistic theory. The findings reveal that new technology has impacted on the traditional uses of punctuation marks. Thus, the results show that the use of punctuation markers in Short Message Service （SMS） texts is complex. Moreover, the use of punctuation marks in Kenyan text messages reveals personal stylistic choices. However, it is apparent that Kenyan text messages are shaped by social variables.
文摘To improve the accuracy of short text matching,a short text matching method with knowledge and structure enhancement for BERT(KS-BERT)was proposed in this study.This method first introduced external knowledge to the input text,and then sent the expanded text to both the context encoder BERT and the structure encoder GAT to capture the contextual relationship features and structural features of the input text.Finally,the match was determined based on the fusion result of the two features.Experiment results based on the public datasets BQ_corpus and LCQMC showed that KS-BERT outperforms advanced models such as ERNIE 2.0.This Study showed that knowledge enhancement and structure enhancement are two effective ways to improve BERT in short text matching.In BQ_corpus,ACC was improved by 0.2%and 0.3%,respectively,while in LCQMC,ACC was improved by 0.4%and 0.9%,respectively.
