一种基于决策树和词义相似度的N1+N2结构语法关系判定方法

设计了一种基于决策树算法的N1+N2结构语法关系判定方法.首先建立了该结构的语料库,对每条语料都标注构建特征集所需的词性、《同义词词林》语义编码、语法关系和词义相似度等信息;然后为证明相似度在判断语法关系中的合理性,根据语言学原理研究了N1+N2结构两个名词间语义相似度与语法关系之间的内在规律:①从语法关系的角度比较两个名词间的语义相似度结果为:并列关系>复指关系>定中关系>主谓关系;②从语言功能焦点的角度比较两个名词间的语义相似度结果为:并焦型短语>后焦型短语.最后以此为基础构建了特征集,运用决策树C4.5算法建立了自动判定N1+N2结构语法关系的方法.运用该算法在自建语料库的测试集中进行测试,正确率为89.39％.     

英语幽默中的双关修辞及其汉译策略

幽默是英语语言文化的重要组成部分,而双关是英语语言实现含蓄表意、达到幽默效果的主要修辞手段。本文通过大量的实例分析、论述,将英语幽默中的双关修辞归纳为语音双关、语义双关和语法双关三大类,并进而提出了英语幽默中双关语的汉译策略。     

自然语言处理用藏语格助词的语法信息研究

该文主要探讨了藏语格助词的语法信息、语义信息、功能结构等内容,从而为建立藏语格助词的语法属性库提供详实的参数。这对句子进行分析与描述,观察句子歧义都有着重要的意义。     

Grammatical evolution in developing optimal inventory policies for serial and distribution supply chains

Recently, there has been a growing literature on biologically inspired algorithms, particularly genetic algorithms and genetic programming, applied to supply chain modelling and inventory control optimisation. Due to the rigidity of the genetic algorithms approach, it is difficult to change the underlying model logic and add richness to the supply chain. While genetic programming provides a more flexible approach than that provided by genetic algorithms, to date its application has been limited to small supply chain modelling problems in relation to optimal inventory policies. This research applies Grammatical Evolution, a relatively new biologically inspired algorithm, to the field of supply chain optimisation, employing human readable rules called grammars. These grammars provide a single mechanism to describe a variety of complex structures and can incorporate the domain knowledge of the practitioner to bias the algorithm towards regions of the search space containing better solutions. Results are presented showing Grammatical Evolution is at least competitive in cost terms, and superior in flexibility, with these methods applicable to any supply chain of the serial or distribution type. Furthermore, Grammatical Evolution shows an adaptive ability that augurs well for supply chains in dynamic environments, such as disruption.     

Noisy Time Series Prediction using Recurrent Neural Networks and Grammatical Inference

Financial forecasting is an example of a signal processing problem which is challenging due to small sample sizes, high noise, non-stationarity, and non-linearity. Neural networks have been very successful in a number of signal processing applications. We discuss fundamental limitations and inherent difficulties when using neural networks for the processing of high noise, small sample size signals. We introduce a new intelligent signal processing method which addresses the difficulties. The method proposed uses conversion into a symbolic representation with a self-organizing map, and grammatical inference with recurrent neural networks. We apply the method to the prediction of daily foreign exchange rates, addressing difficulties with non-stationarity, overfitting, and unequal a priori class probabilities, and we find significant predictability in comprehensive experiments covering 5 different foreign exchange rates. The method correctly predicts the directionof change for the next day with an error rate of 47.1%. The error rate reduces to around 40% when rejecting examples where the system has low confidence in its prediction. We show that the symbolic representation aids the extraction of symbolic knowledge from the trained recurrent neural networks in the form of deterministic finite state automata. These automata explain the operation of the system and are often relatively simple. Automata rules related to well known behavior such as tr end following and mean reversal are extracted.     

语法依存性与语言习得中的非语法程序安排

语法的基本特征如抽象性、生成性、层次性等是从学术研究的角度归纳出来的．并未真正触及语法的本质属性,即语法实质：语法是人们所使用的语言的表达习惯。语法依存性作为语法的一个本质特点也长期为人们所忽略,它指的是语法在人类大脑里的内化,对语言现实的不可剥离性。而正因为对语法实质及语法依存性的认知不足,使得语言学习者的学习策略和学习重心产生偏误,违背了最初的学习目的。母语习得过程中的非语法程序安排对语言习得理论及其实践应该有更多的指导作用。     

A method for transforming grammars into LL(k) form

Summary A new method for transforming grammars into equivalent LL(k) grammars is studied. The applicability of the transformation is characterized by defining a subclass of LR(k) grammars, called predictive LR(k) grammars, with the property that a grammar is predictive LR(k) if and only if the corresponding transformed grammar is LL(k). Furthermore, it is shown that deterministic bottom-up parsing of a predictive LR(k) grammar can be done by the LL(k) parser of the transformed grammar. This parsing method is possible since the transformed grammar always left-to-right covers the original grammar. The class of predictive LR(k) grammars strictly includes the class of LC(k) grammars (the grammars that can be parsed deterministically in the left-corner manner). Thus our transformation is more powerful than the one previously available, which transforms LC(k) grammars into LL(k) form.     

汉英句子的特征与汉英翻译实践

“句子的外部形式”是句子的表层结构,人类说话之前存在于头脑之中的连贯意念称为句子的深层结构。汉语句子和英语句子正是通过深层结构这个桥梁连接起来,这是两种语言的互译的前提。根据汉语句子和英语句子表层结构的不同,总体上可将汉语句子归纳为七类,以应用于翻译实践。     

Heuristic Algorithms for Determination of Canonical Forms and Grammatical Characteristics of Words

Algorithms are developed that determine canonic forms and grammar categories from individual words and the vocabulary of a text. Algorithms are proved to be highly efficient. The accuracy of determination directly depends on the length of the text.     

一个上下文无关文法的构造定理及其在推断中的应用

递归概念可以在句子中重复派生、循环出现。对这样的句子推断时,若为递归概念的每一个派生部分引进一个递归概念来描述,将推断出多个与之有相似的产生式结构的递归概念,同时也构造出一个新文法。本文先给出新文法的形式化构造方法,证明了新文法与原文法的等价性。在文章的后部,通过实例,介绍该定理在简化复杂文法推断中的应用。