An empirical study is conducted to examine the effect of constructing sense relations in vocabulary teaching. Fifty subjects are divided into two groups： the controlled group which was taught with traditional method,...An empirical study is conducted to examine the effect of constructing sense relations in vocabulary teaching. Fifty subjects are divided into two groups： the controlled group which was taught with traditional method, and the experimental group to which sense relation strategy was applied in vocabulary instruction. At the end of the experiment instruction, a test （depth of vocabulary knowledge measure） was given to examine the teaching effects of the two vocabulary teaching strategies. The target words in the tests were selected from the word list that had been taught during the experiment time. A delayed vocabulary posttest was given to the subjects two weeks after examining the long-term retention effect. The third test was administered with different targets words which were selected from a different intensive reading material which wass new to the subjects. The experiment proves that constructing sense relations in vocabulary teaching could produce satisfactory results by enhancing students＇ lexical capacity and long-term retention.展开更多
Automatic classification of sentiment data（e.g., reviews, blogs） has many applications in enterprise user management systems, and can help us understand people＇s attitudes about products or services. However, it is...Automatic classification of sentiment data（e.g., reviews, blogs） has many applications in enterprise user management systems, and can help us understand people＇s attitudes about products or services. However, it is difficult to train an accurate sentiment classifier for different domains. One of the major reasons is that people often use different words to express the same sentiment in different domains, and we cannot easily find a direct mapping relationship between them to reduce the differences between domains. So, the accuracy of the sentiment classifier will decline sharply when we apply a classifier trained in one domain to other domains. In this paper, we propose a novel approach called words alignment based on association rules（WAAR） for cross-domain sentiment classification,which can establish an indirect mapping relationship between domain-specific words in different domains by learning the strong association rules between domain-shared words and domain-specific words in the same domain. In this way, the differences between the source domain and target domain can be reduced to some extent, and a more accurate cross-domain classifier can be trained. Experimental results on Amazon~ datasets show the effectiveness of our approach on improving the performance of cross-domain sentiment classification.展开更多
文摘An empirical study is conducted to examine the effect of constructing sense relations in vocabulary teaching. Fifty subjects are divided into two groups： the controlled group which was taught with traditional method, and the experimental group to which sense relation strategy was applied in vocabulary instruction. At the end of the experiment instruction, a test （depth of vocabulary knowledge measure） was given to examine the teaching effects of the two vocabulary teaching strategies. The target words in the tests were selected from the word list that had been taught during the experiment time. A delayed vocabulary posttest was given to the subjects two weeks after examining the long-term retention effect. The third test was administered with different targets words which were selected from a different intensive reading material which wass new to the subjects. The experiment proves that constructing sense relations in vocabulary teaching could produce satisfactory results by enhancing students＇ lexical capacity and long-term retention.
基金Project supported by the National Natural Science Foundation of China(Nos.61703013,91546111,91646201,61672070,and61672071)the Beijing Municipal Natural Science Foundation(No.4152005)+1 种基金the Key Projects of Beijing Municipal Education Commission(Nos.KZ201610005009 and KM201810005024)the International Cooperation Seed Grant from Beijing University of Technology of 2016(No.007000514116520)
文摘Automatic classification of sentiment data（e.g., reviews, blogs） has many applications in enterprise user management systems, and can help us understand people＇s attitudes about products or services. However, it is difficult to train an accurate sentiment classifier for different domains. One of the major reasons is that people often use different words to express the same sentiment in different domains, and we cannot easily find a direct mapping relationship between them to reduce the differences between domains. So, the accuracy of the sentiment classifier will decline sharply when we apply a classifier trained in one domain to other domains. In this paper, we propose a novel approach called words alignment based on association rules（WAAR） for cross-domain sentiment classification,which can establish an indirect mapping relationship between domain-specific words in different domains by learning the strong association rules between domain-shared words and domain-specific words in the same domain. In this way, the differences between the source domain and target domain can be reduced to some extent, and a more accurate cross-domain classifier can be trained. Experimental results on Amazon~ datasets show the effectiveness of our approach on improving the performance of cross-domain sentiment classification.
