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.

基于观点袋模型的汽车评论情感极性分类

该文针对网络评论倾向分级问题,提出了一种基于观点袋模型和语言学规则的多级情感分类方法。通过分析句子中的词性搭配关系,设计了12种抽取特征-观点搭配模式,并对存在问题给出了解决策略。依据汉语用词特点和词汇在汽车领域的特殊用法,提出搭配四元组的情感倾向极性值计算方法。在此基础上,利用获取的搭配四元组及其情感倾向极性,建立文本的向量化表示,并构造了权重计算公式。最后,利用文本余弦相似度计算方法实现对评论文本的五级情感极性分类。通过在COAE2012任务3的汽车数据集上进行的测试,取得了较好的分类结果。

基于模式匹配与半监督学习的评价对象抽取

针对产品评论中评价对象的抽取问题,提出一种基于模式匹配与半监督学习的抽取方法。通过大量样本统计,获得种子规则集,以抽取有效评价句,利用句法结构组合以及词性距离相关性算法抽取评价对象,将种子规则和评价对象存入相应的模式库,并通过半监督学习方法与规则的动态替换,进行规则的学习与评价对象的扩充训练。实验结果表明,该方法的抽取效果较好,证明了方法的可行性。

规则与统计结合的俄语基本名词短语识别

针对目前国内鲜有研究且语料资源缺乏的俄语基本名词短语(Base Noun Phrase,Base NP)识别,提出一种规则与统计相结合的方法,其优势是在有限资源的基础上,既能充分利用俄语Base NP在词性构成上的规律特点,通过俄汉词典统计得到最佳词性搭配模式库进行模式匹配;又无需人工标注统计工具所需的训练语料,仅依靠词典和词性搭配模式库自动构建,节省标注代价。规则与统计的结合,既能在很大程度上召回Base NP,又能使用条件随机场(Conditional Random Fields,CRF)纠正规则标注的歧义和错误,处理规则未能覆盖的情况。实验表明,使用该方法实现的俄语基本名词短语识别效果良好,其F值达到了84.14%。

常用英语否定前缀解析

词缀法是构词法的一种,在英语词汇的发展中起着非常重要的作用。根据词缀在词中的位置,可以划分为前缀,中缀和后缀。本文主要从以下几个方面分析常见的否定前缀:(1)常用否定前缀的语义特征。(2)常用否定前缀构词的特点。(3)常见否定前缀的应用规则。通过研究,本文旨在帮助英语学习者对常见否定前缀有更深刻的认识并且有效扩充词汇量。

词语模“XX人”与“XX者”比较研究

文章从词性搭配、语义、语用角度比较分析“XX人”与“XX者”词语模的异同,溯源“人”“者”的源义,探究二者的广泛的能产性、构词特点及表达效果。