基于最大熵的汉语篇章结构自动分析方法

在标有复句逻辑语义关系的清华汉语树库上, 研究汉语篇章语义片段自动切分以及篇章关系的自动标注方法。通过比较不同序列标注模型对汉语篇章语义单元切分的性能, 提出基于最大熵模型的汉语篇章结构分析方法。实验结果表明, 篇章语义单元自动切分的F值能达到89.1%, 当篇章语义结构树的高度不超过6层时, 篇章语义关系标注的F值为63%。     

英汉数词的"言外之意"

英汉语数词的语义转换、语义重构与修辞手段的运用呈现出不同方式,从而产生出大量的"言外之意、弦外之音".研究和对比英汉语数词的"言外之意",有助于对英汉语的认知与解码.     

汉语动词多义聚合网络的认知建构

动词是汉语最重要的一个词类,多义动词的义项通过家族相似性聚合成语义网络。汉语动词多义聚合网络的类型主要有辐射式聚合网络、链条式聚合网络、综合式聚合网络。汉语动词多义聚合网络的形成是通过隐喻、转喻的方式实现的。同时,研究汉语动词多义聚合时也要充分考虑到词义的模糊性。通过对汉语动词多义聚合网络的分析,可以更好地了解动词义项的聚合规律,进而了解整个汉语语义的聚合规律,为认知语义字典、词典的编纂提供有益借鉴。     

汉语计算语义理论及其原则

介绍了一些汉语计算语义理论相关的知识和研究成果,谈到了目前面临的问题,最后提出了汉语计算语义理论研究的目标、原则与思路,以作为解决问题的对策.     

汉语语法的三元系统

语形、语义、语值、语境是汉语语法的基本要素,是研究、解释汉语语法事实和语法理论的基本前提。因而,从“语形、语义、语值、语境”角度切入,结合不同的相关因素,可以构建汉语语法的制约系统、证明系统、柔性系统。     

现代汉语词汇语义网模型设计

在深刻剖析WordNet、HowNet的基础上，针对汉语的特点提出以“字义基元化，词义组合化”为基本观点来研究汉语词汇语义网，并建造了一个汉语词汇语义网模型．     

英语中的幽默手法Tom Swifties初论

英语中有一种类似汉语歇后语、能表达双关和幽默的语言形式：Tom Swifties。它的语义建构机制与汉语歇后语有很多相似之处，都采用谐音法、语义双关法、拆字法以及典故法等基本语义建构模式。由于它和汉语歇后语有很多相似之处，所以可以将其翻译为“英式歇后语”。对Tom Swifties语义建构机制的研究可以让我们更好地理解英语的这种幽默手法。     

徐通锵“字”本位思想探析

本文旨在评述徐通锵先生提出的字本位观并据此形成的汉语语义句法思想,从“字”和汉语基本结构单位,“字”本位和汉语语义句法两方面入手简要揭示了徐通锵“字”本位说的主要内容,并深入剖析了其形成因素,最后指出徐通锵先生提出、创立字本位说,对于汉语研究摆脱机械模仿,走上独立研究、自主创新的道路,无疑具有革命性的意义。     

浅谈汉语语言学研究

从汉语语言学的发展历史和研究现状来考察,汉语语法学在目前应该继续努力学习西方语言学理论,适当借鉴汉语传统语义研究的成果和方法,与世界语言学协调发展,并尝试构建适合汉语的语言理论和语言研究方法.     

汉字是汉语研究的中心主题

本文通过对汉字与汉语音节的关系、汉字在字音研究、字义和语义句法中的作用的研究,得出汉语研究应该以汉字作为中心主题的结论。只有确立汉字在汉语研究中的中心主题地位,依据汉语的特质进行研究,才能够使汉语研究有一个新的大发展。     

形容词多义性在《现代汉语规范词典》中的表征

通过对127个高频形容词在《现代汉语规范词典》中的释义进行统计分析,发现了一种新的一词多义表征方式——同义词或反义词加语义特征。采用“三步法”,可以全面收集某个形容词在词库中的同义词、反义词和相关特征,包括那些没有在本词条下出现的词和特征。这项研究在一定程度上增进了对“互训”和语义特征的认识,有助于进一步开展相关的语义学和自然语言处理研究。     

英、法、汉语构词途径的哲学思辨与对比

从哲学视角和语义学出发对英、法、汉构词途径及其约定俗成的规则进行思辨性、交叉式的析比，辨明其间的异同之处，探寻英、法、汉语基本词的命名（构词）理据及其基本语义特征和语义拓展延伸路径，揭示不同语种语言发展的哲学奥秘，探索中西语言文化的普遍发展规律。     

Two Language Models Using Chinese Semantic Parsing

Introduction Although the word trigram dominates the statistical language modeling community, it still has some short- comings. For example, the word trigram cannot make use of the rich linguistic structure of the language, nor can it capture long-distanc…     

Contrastive Analysis of the Middle Construction

The English Middle Construction (EMC), as a piculiar syntactic structure, shares its semantic features, but diversifies in its syntactic configuration compared with other langtages. This paper tries to have a contrast study of the Middle Construcitons between English and Chinese and find the two languages share the same semantic features that the incompatibility between the semantic quantitatives (SQs) of the Adverb (Adjunct in the syntactic term) and the SQs of the Verb denoted by the predicate of MC leads to the deactivization of the predicate by means of the Adjunct, functioning as a quantitative device, assign delimitation to the predicate, hence ensures the grammaticality of the construction. But syntatically, we agree that the NP Movement Approach accounts for the formation of EMC, while we argue in Chinese it is the verb raising that results in the MC. This paper f‘n-st represents the structural representation of the English Middle Construction; then the structural analysis is elaborated in comparison with that in Chinese, based on the previous studies; and finally the motivations of the Ecs in the perspective of syntactic and semantic functions are explored and hence a new hypothesis is raised to probe the similar construction in Chinese.     

基于关联规则挖掘的汉语语义搭配规则获取方法

针对自然语言处理系统在短语分析时的词汇排歧和结构排歧需要,本文提出了一种基于语料库的汉语短语语义搭配规则自动获取方法.该方法以《知网》为语义知识资源,在标注了句法语义信息的汉语短语熟语料库基础上,先采用数据挖掘中元规则制导的交叉层关联规则挖掘方法,自动发现汉语短语的语义搭配规律,再根据统计结果自动优选后生成语义搭配规则库.实验结果表明该方法是切实可行的.运用该方法自动获取的语义搭配规则具有较好的排歧效果.     

形状形容词“直”的逻辑语义分析

“直”是高频的形状形容词，在传统词汇语义分析的基础上，运用逻辑语义学理论以“直”为个案考察形状形容词“直”在不同分布中的语义结构关系，旨在初步建立汉语形状形容词的逻辑语义模型及理解模式，可以为进一步形式化提供语义信息和知识，从而为中文信息处理的词义分析提供一种新的思路。     

Chinese Semantic Parsing Based on Feature Structure with Recursive Directed Graph

It is difficult to analyze semantic relations automatically, especially the semantic relations of Chinese special sentence patterns. In this paper, we apply a novel model feature structure to represent Chinese semantic relations, which is formalized as "recursive directed graph". We focus on Chinese special sentence patterns, including the complex noun phrase, verb-complement structure, pivotal sentences, serial verb sentence and subject-predicate predicate sentence. Feature structure facilitates a richer Chinese semantic information extraction when compared with dependency structure. The results show that using recursive directed graph is more suitable for extracting Chinese complex semantic relations.     

Chinese semantic processing cerebral areas

This study has identified the active cerebral areas of normal Chinese that are associated with Chinese semantic processing using functional brain imaging. According to the traditional cognitive theory, semantic processing is not particularly associated with or affected by input modality. The functional brain imaging experiments were conducted to identify the common active areas of two modalities when subjects perform Chinese semantic tasks through reading and listening respectively. The result has shown that the common active areas include left inferior frontal gyrus (BA 44/45), left posterior inferior temporal gyrus (BA37); the joint area of inferior parietal Iobules (BA40) and superior temporal gyrus, the ventral occipital areas and cerebella of both hemispheres. It gives important clue to further discerning the roles of different cerebral areas in Chinese semantic processing.