分词是非谓语动词中的一种。如果使用得当会使句子简单明了,然而由于理解有误,学生在使用中常常出错。现将学生练习中常出现的错误归纳总结如下: 一、分词做定语 1.分词作定语时,如果被修饰词是施动者,用现在分词;如果被修饰词承受动作...分词是非谓语动词中的一种。如果使用得当会使句子简单明了,然而由于理解有误,学生在使用中常常出错。现将学生练习中常出现的错误归纳总结如下: 一、分词做定语 1.分词作定语时,如果被修饰词是施动者,用现在分词;如果被修饰词承受动作,则用过去分词。例如: 昨晚收到的信是妈妈寄来的。误:The letter receivinglast night is from mother.展开更多
A local and global context representation learning model for Chinese characters is designed and a Chinese word segmentation method based on character representations is proposed in this paper. First, the proposed Chin...A local and global context representation learning model for Chinese characters is designed and a Chinese word segmentation method based on character representations is proposed in this paper. First, the proposed Chinese character learning model uses the semanties of loeal context and global context to learn the representation of Chinese characters. Then, Chinese word segmentation model is built by a neural network, while the segmentation model is trained with the eharaeter representations as its input features. Finally, experimental results show that Chinese charaeter representations can effectively learn the semantic information. Characters with similar semantics cluster together in the visualize space. Moreover, the proposed Chinese word segmentation model also achieves a pretty good improvement on precision, recall and f-measure.展开更多
This paper proposes a new way to improve the performance of dependency parser: subdividing verbs according to their grammatical functions and integrating the information of verb subclasses into lexicalized parsing mod...This paper proposes a new way to improve the performance of dependency parser: subdividing verbs according to their grammatical functions and integrating the information of verb subclasses into lexicalized parsing model. Firstly,the scheme of verb subdivision is described. Secondly,a maximum entropy model is presented to distinguish verb subclasses. Finally,a statistical parser is developed to evaluate the verb subdivision. Experimental results indicate that the use of verb subclasses has a good influence on parsing performance.展开更多
ESA is an unsupervised approach to word segmentation previously proposed by Wang, which is an iterative process consisting of three phases: Evaluation, Selection and Adjustment. In this article, we propose Ex ESA, the...ESA is an unsupervised approach to word segmentation previously proposed by Wang, which is an iterative process consisting of three phases: Evaluation, Selection and Adjustment. In this article, we propose Ex ESA, the extension of ESA. In Ex ESA, the original approach is extended to a 2-pass process and the ratio of different word lengths is introduced as the third type of information combined with cohesion and separation. A maximum strategy is adopted to determine the best segmentation of a character sequence in the phrase of Selection. Besides, in Adjustment, Ex ESA re-evaluates separation information and individual information to overcome the overestimation frequencies. Additionally, a smoothing algorithm is applied to alleviate sparseness. The experiment results show that Ex ESA can further improve the performance and is time-saving by properly utilizing more information from un-annotated corpora. Moreover, the parameters of Ex ESA can be predicted by a set of empirical formulae or combined with the minimum description length principle.展开更多
The concept of word classes （parts of speech） has always generated controversy among linguists. The earlier Prescriptive and Descriptive Schools might have set the pace for this controversy but the present dilemma i...The concept of word classes （parts of speech） has always generated controversy among linguists. The earlier Prescriptive and Descriptive Schools might have set the pace for this controversy but the present dilemma is much deeper. Learners and even teachers are sometimes at quandary as to how to proof that a particular word belongs to a particular class. This is because a word may sometimes belong to several classes, in context as in the word ＂watch＂ which can belong to different classes. This paper therefore tries to provide answers to the problem of word class classification by using a morphological and syntactical evidence to prove that English words follow a particular range of inflections and belong to strictly ordered particular categories and do not change their class arbitrarily. This is in line with the natural perfect order of homogeneity in creation which precludes a specie from merging effectively with another specie without having to undergo some fundamental changes. Other variables were also looked into and it was concluded that teachers and learners as well, can rely on this sub-categorization approach as a reliable paradigm for their assumptions concerning word classes.展开更多
文摘分词是非谓语动词中的一种。如果使用得当会使句子简单明了,然而由于理解有误,学生在使用中常常出错。现将学生练习中常出现的错误归纳总结如下: 一、分词做定语 1.分词作定语时,如果被修饰词是施动者,用现在分词;如果被修饰词承受动作,则用过去分词。例如: 昨晚收到的信是妈妈寄来的。误:The letter receivinglast night is from mother.
基金Supported by the National Natural Science Foundation of China(No.61303179,U1135005,61175020)
文摘A local and global context representation learning model for Chinese characters is designed and a Chinese word segmentation method based on character representations is proposed in this paper. First, the proposed Chinese character learning model uses the semanties of loeal context and global context to learn the representation of Chinese characters. Then, Chinese word segmentation model is built by a neural network, while the segmentation model is trained with the eharaeter representations as its input features. Finally, experimental results show that Chinese charaeter representations can effectively learn the semantic information. Characters with similar semantics cluster together in the visualize space. Moreover, the proposed Chinese word segmentation model also achieves a pretty good improvement on precision, recall and f-measure.
基金the National Natural Science Foundation of China (No.60435020, 60575042 and 60503072).
文摘This paper proposes a new way to improve the performance of dependency parser: subdividing verbs according to their grammatical functions and integrating the information of verb subclasses into lexicalized parsing model. Firstly,the scheme of verb subdivision is described. Secondly,a maximum entropy model is presented to distinguish verb subclasses. Finally,a statistical parser is developed to evaluate the verb subdivision. Experimental results indicate that the use of verb subclasses has a good influence on parsing performance.
基金supported in part by National Science Foundation of China under Grants No. 61303105 and 61402304the Humanity & Social Science general project of Ministry of Education under Grants No.14YJAZH046+2 种基金the Beijing Natural Science Foundation under Grants No. 4154065the Beijing Educational Committee Science and Technology Development Planned under Grants No.KM201410028017Beijing Key Disciplines of Computer Application Technology
文摘ESA is an unsupervised approach to word segmentation previously proposed by Wang, which is an iterative process consisting of three phases: Evaluation, Selection and Adjustment. In this article, we propose Ex ESA, the extension of ESA. In Ex ESA, the original approach is extended to a 2-pass process and the ratio of different word lengths is introduced as the third type of information combined with cohesion and separation. A maximum strategy is adopted to determine the best segmentation of a character sequence in the phrase of Selection. Besides, in Adjustment, Ex ESA re-evaluates separation information and individual information to overcome the overestimation frequencies. Additionally, a smoothing algorithm is applied to alleviate sparseness. The experiment results show that Ex ESA can further improve the performance and is time-saving by properly utilizing more information from un-annotated corpora. Moreover, the parameters of Ex ESA can be predicted by a set of empirical formulae or combined with the minimum description length principle.
文摘The concept of word classes （parts of speech） has always generated controversy among linguists. The earlier Prescriptive and Descriptive Schools might have set the pace for this controversy but the present dilemma is much deeper. Learners and even teachers are sometimes at quandary as to how to proof that a particular word belongs to a particular class. This is because a word may sometimes belong to several classes, in context as in the word ＂watch＂ which can belong to different classes. This paper therefore tries to provide answers to the problem of word class classification by using a morphological and syntactical evidence to prove that English words follow a particular range of inflections and belong to strictly ordered particular categories and do not change their class arbitrarily. This is in line with the natural perfect order of homogeneity in creation which precludes a specie from merging effectively with another specie without having to undergo some fundamental changes. Other variables were also looked into and it was concluded that teachers and learners as well, can rely on this sub-categorization approach as a reliable paradigm for their assumptions concerning word classes.
