语料库词性标注一致性检查方法研究

在对大规模语料库进行深加工时 ,保证词性标注的一致性已成为建设高质量语料库的首要问题。本文提出了基于聚类和分类的语料库词性标注一致性检查的新方法 ,该方法避开了以前一贯采用的规则或统计的方法 ,利用聚类和分类的思想 ,对范例进行聚类并求出阈值 ,对测试数据分类来确定其标注的正误 ,进而得出每篇文章的词性标注一致性情况 。

基于分类的汉语语料库词性标注一致性检查

制约语料库加工质量的一个重要方面是多标记词语的词性标注一致性问题。该文通过对大规模语料库兼类词的词性标注结果的分析,提出一种语料库词性标注一致性检查的方法,分析词性标记序列的特征并建立兼类词语境向量模型,运用k最近邻法,对兼类词语境进行向量分类,判定兼类词词性标注是否一致,得出每篇文章的词性标注的一致性情况,并测试了北京大学的150万语料。

Effects of Collocational Congruency,Frequency and L2 Proficiency on the Processing of English Adjective-Noun Collocations

The present study investigates the effects of congruency and frequency on adjective-noun collocational processing for Chinese learners of English at two proficiency levels based on the data obtained in an online acceptability judgment task.The subject pool of this research included 60 English majors studying at a university in China;30 were selected as a higher-proficiency group and 30 as a lower-proficiency group according to their Vocabulary Levels Test(Schmitt et al.,2001)scores and their self-reported proficiency in English.The experimental materials were programmed to E-prime 2.0 and included six types of collocations:(1)15 high-frequency congruent collocations,(2)15 low-frequency congruent collocations,(3)15 high-frequency incongruent collocations,(4)15 low-frequency incongruent collocations,(5)15 Chinese-only items,and(6)75 unrelated items for baseline data.The collected response times(RTs)and accuracy rates data were statistically analyzed by the use of an ANOVA test and pairwise comparisons through SPSS 16.0 software.The results revealed that:(1)the adjective-noun collocational processing of Chinese English learners is influenced by collocational frequency,congruency and L2 proficiency;(2)the processing time is affected by the interaction of congruency and frequency;and(3)the interactive effect of L2 proficiency in conjunction with congruency and frequency also influences the processing quality.

论汉语颜色反义词的构成机制

汉语颜色反义词的构成机制包括三个层次的限制,首先是逻辑层次上的全异关系限制,其次是语义层次上的反义关系限制,最后要遵循语音语法的相关规则。