Expression of syntactic and semantic features in logic-based grammars

In this paper, we introduce and initiate a formalism to represent syntactic and semantic features in logic-based grammars. We also introduce technical devices to express feature-checking and feature-inheritance mechanisms. This leads us to propose some extensions to the basic unification mechanism of PROLOG. Finally, we consider the problem of long-distance dependency relations between constituents in gapping grammars rules from the point of view of morphosyntactic features that may change depending on the position occupied by the moved constituents. What we propose is not a new linguistic theory about features, but rather a formalism and a set of tools that we think will be useful to grammar writers to describe features and their relations in grammar rules.     

语义分析中谓词标识的特征工程

谓词是句子中的最重要的成分,它的正确与否对语义分析的影响非常大。而众多的特征直接影响到谓词标识的性能,如何组织这些特征显得尤为重要。选取了7个基本特征和30多个新特征以及它们的组合,使用最大熵分类器,在基本特征的基础上通过增加有利特征的方法,使得谓词标注的F1值增长了约5%（由84.7%增加到89.8%）,词义识别的F1值增长了约2%（由80.3%增加到82.1%）,结果表明,这些新特征及其组合大大提高了性能。     

基于特征组合的中文语义角色标注

提出一种基于特征组合和支持向量机(support vector machine,简称SVM)的语义角色标注(semantic role labeling,简称SRL)方法.该方法以句法成分作为基本标注单元,首先从当前基于句法分析的语义角色标注系统中选出高效特征,构成基本特征集合.然后提出一种基于统计的特征组合方法.该方法能够根据正反例中组合特征的分布状况,以类间距离和类内距离之比作为统计量来衡量组合特征对分类所产生的效果,保留分类效果较好的组合特征.最后,在Chinese PropBank(CPB)语料上利用支持向量机进行分类实验,结果表明,引入该特征组合方法后,语义角色标注整体F值达91.81%,提高了近2%.     

One-sided forbidding grammars and selective substitution grammars

In one-sided forbidding grammars, the set of rules is divided into the set of left forbidding rules and the set of right forbidding rules. A left forbidding rule can rewrite a non-terminal if each of its forbidding symbols is absent to the left of the rewritten symbol in the current sentential form, while a right forbidding rule is applied analogically except that this absence is verified to the right. Apart from this, they work like ordinary forbidding grammars. As its main result, this paper proves that one-sided forbidding grammars are equivalent to selective substitution grammars. This equivalence is established in terms of grammars with and without erasing rules. Furthermore, this paper proves that one-sided forbidding grammars in which the set of left forbidding rules coincides with the set of right forbidding rules characterize the family of context-free languages. In the conclusion, the significance of the achieved results is discussed.     

一种基于词对齐的中文深层语义解析模型

语义解析是指将自然语言句子转化成便于机器理解和推理的意义形式。近年来英文语义解析的研究取得了很大进展。然而,中文语义解析的相关工作则相对较少。中文和英文之间存在一定的差异,适用于英文的语义解析方法不一定适合中文。因此,针对中文的语言特点,提出一种基于词对齐的中文语义解析方法,将中文句子转化成其相应的意义表示看作是一个机器翻译的过程。首先将英文语义解析方法中常用的训练数据集GEOQUERY转化成中文数据集,数据集中每条训练数据包括一个中文句子及其正确的意义表示。然后利用词对齐模型来获取由中文自然语言字符串及其相应的意义表示所组成的双语词典。最后通过学习一个概率估计模型来确定最终的语义解析模型。实验结果表明,WACSP有较高的精确度和覆盖率。     

Reversible logic grammars for natural language parsing and generation

The use of a single grammar in natural language parsing and generation is most desirable for a variety of reasons, including efficiency, perspicuity, integrity, robustness, and a certain amount of elegance. These characteristics have been noted before by several researchers, but it was only recently that more serious attention started to be paid to the problem of creating a bidirectional system for natural language processing. In this paper we discuss a somewhat more radical version of the problem: given a parser for a language, can we reverse it so that it becomes an efficient generator for the same language? Furthermore, since both the parser and the generator are based upon the same grammar, are there any normalization conditions upon the form of the grammar that must be met in order to assure the maximum efficiency of the reversed program? Can other grammars be transformed into the normal form? We describe the results of an experiment with PROLOG-based logic grammar which has been derived from a substantial-coverage string grammar for English. We present an alogorithm for automated inversion of a unification parser into an efficient unification generator, using the collections of minimal sets of essential arguments for predicates. We discuss the scope of the present version of the algorithm and then point out several possible avenues for extension. We also outline a preliminary solution to the question of grammar's “normal form” and suggest a handful of normalizing transformations that can be used to enhance the efficiency of the generator. This research interacts closely with a Japanese-English machine translation project at New York University, for which the first implementation of the inversion algorithm has been prepared.     

浅层语义分析及SPARQL在问答系统中的应用

为了解决受限域问答系统中答案抽取的问题,提出了一种基于浅层语义分析的问答系统模型。该模型以自然语言为接口,利用医院信息本体,采用浅层语义分析技术,由语义块定义规则和语义块判定规则,首先生成问句向量,然后利用SPARQL查询技术,在本体中进行查询,从而得到答案。实验表明该方法可行,对自动问答系统的设计具有借鉴意义和深入研究的价值。     

结合特征图切分的图像语义分割

目的 基于全卷积神经网络的图像语义分割研究已成为该领域的主流研究方向。然而,在该网络框架中由于特征图的多次下采样使得图像分辨率逐渐下降,致使小目标丢失,边缘粗糙,语义分割结果较差。为解决或缓解该问题,提出一种基于特征图切分的图像语义分割方法。方法 本文方法主要包含中间层特征图切分与相对应的特征提取两部分操作。特征图切分模块主要针对中间层特征图,将其切分成若干等份,同时将每一份上采样至原特征图大小,使每个切分区域的分辨率增大;然后,各个切分特征图通过参数共享的特征提取模块,该模块中的多尺度卷积与注意力机制,有效利用各切块的上下文信息与判别信息,使其更关注局部区域的小目标物体,提高小目标物体的判别力。进一步,再将提取的特征与网络原输出相融合,从而能够更高效地进行中间层特征复用,对小目标识别定位、分割边缘精细化以及网络语义判别力有明显改善。结果 在两个城市道路数据集CamVid以及GATECH上进行验证实验,论证本文方法的有效性。在CamVid数据集上平均交并比达到66.3%,在GATECH上平均交并比达到52.6%。结论 基于特征图切分的图像分割方法,更好地利用了图像的空间区域分布信息,增强了网络对于不同空间位置的语义类别判定能力以及小目标物体的关注度,提供更有效的上下文信息和全局信息,提高了网络对于小目标物体的判别能力,改善了网络整体分割性能。     

藏文语义词典建设中语义关系抽取方法的研究

研究语义是当前人工智能、语义网、语义词典等研究领域的热点,它可以有效支持机器翻译和自然语言处理等技术.文章根据藏文独特的文法特性,运用藏文逻辑格和计算语言学知识,在保留藏文原有特点的基础上,为藏文语义关系抽取方法建立较完整的语义场,以此为藏文语义词典建设提供了基础性构建方法.     

A graph grammars based framework for querying graph-like data

The widespread use of graph-based models for representing data collections (e.g. object-oriented data, XML data, etc.) has stimulated the database research community to investigate the problem of defining declarative languages for querying graph-like databases. In this paper, a new framework for querying graph-like data based on graph grammars is proposed. The new paradigm allows us to verify structural properties of graphs and to extract sub-graphs. More specifically, a new form of query (namely graph query) is proposed, consisting in a particular graph grammar which defines a class of graphs to be matched on the graph representing the database. Thus, differently from path queries, the answer of a graph query is not just a set of nodes, but a subgraph, extracted from the input graph, which satisfies the structural properties defined by the graph grammar. Expressiveness and complexity of different forms of graph queries are discussed, and some practical applications are shown.     

基于语义角色标注的文本水印算法

为保护数字文本的知识产权,提出一种利用语义角色嵌入水印信息的文本水印算法。采用Unicode编码和Huffman编码对水印进行预处理形成特定形式的水印信息串,借助自然语言处理技术标注文本中的语义角色,将水印信息映射为语义角色的位置,实现水印的嵌入与提取。算法对文本的格式和内容不做任何修改,具有很强的隐蔽性和鲁棒性,能有效抵抗常见的格式变换和攻击,同时能提供较大的水印容量,与其它文本水印算法相比具有一定的优越性。     

Chinese-based research on subject-covered information retrieval supervised by textual semantic domain

By means of analysis of artificial intervention in ready-retrieved text, training set used to compare with new texts from large-scale real texts corpus is provided. It is based on the data-originated presentation of training set that a special formula to calculate semantic cohesion between new texts and training set is devised. The semantic cohesion of new text is the average value of semantic evaluation of all elements involved, and semantic evaluation of an element depends on its semantic relevance with the training set and on the semantic ratio of its domain to synonymous domain. In terms of empirical verification a conclusion is drawn that semantic cohesion is the key measurement standard of textual retrieval. Despite the advantages of textual retrieval, limitations of formula-raised condition and analyst＇s accomplishments make the analysis involved in this paper imperfect.     

Analysis and generation grammars

This paper describes the analysis and generation grammars for English and Japanese as they were employed in the KBMT-89 program. We discuss word order, coordination, subcategorization, morphological rules, rule ordering and bi-directional grammars.     

视频语义分析运动特征表征与抽取技术研究

视频运动特征蕴含丰富的语义信息,运动特征的简洁表征方式和高效抽取方法研究是视频语义分析的关键技术之一。针对视频语义分析的特点,将运动特征分为3类,分别对各类运动特征进行表征和抽取。相关抽取实验证明此方法可有效抽取语义分析所需的运动特征,同时在运动特征抽取的基础上实现了基于运动的视频语义分析原型系统。     

基于语义网格的反垃圾邮件应用架构设计

目前对垃圾邮件问题的大部分解决方法仍受到互联网自身特性的限制,而且在较大范围内邮件过滤的准确率也不能满足人们的要求.因此从语义网格的角度出发,利用语义网格的语义分析能力强且具有网格优势等特点来解决垃圾邮件问题.提出反垃圾邮件语义网格的概念,并详细阐述了反垃圾邮件语义网格系统的基本思想、体系结构以及支撑技术;利用OptorSim网格模拟器对系统进行测试;对系统中一些关键问题进行讨论.     

Ll-regular grammars

Culik II and Cohen introduced the class of LR-regular grammars, an extension of the LR(k) grammars.

In this paper we consider an analogous extension of the LL(k) grammars called the LL- regular grammars. The relation of this class of grammars to other classes of grammars will be shown. Any LL-regular grammars is an LR-regular grammar. Properties of LL(k) grammars can be generalized to properties of LL-regular grammars.     

Attribute grammars for scalable query processing on XML streams

We introduce the notion of XML Stream Attribute Grammars (XSAGs). XSAGs are the first scalable query language for XML streams (running strictly in linear time with bounded memory consumption independent of the size of the stream) that allows for actual data transformations rather than just document filtering. XSAGs are also relatively easy to use for humans. Moreover, the XSAG formalism provides a strong intuition for which queries can or cannot be processed scalably on streams. We introduce XSAGs together with the necessary language-theoretic machinery, study their theoretical properties such as expressiveness and complexity, and discuss their implementation.     

Inference for transition network grammars

This paper gives a brief introduction to transition networks and proposes an approach to the inference of transition network grammars.     

基于语义向量表示的查询扩展方法

针对传统查询扩展方法在专业领域中扩展词与原始查询之间缺乏语义关联的问题,提出一种基于语义向量表示的查询扩展方法。首先,构建了一个语义向量表示模型,通过对语料库中词的上下文语义进行学习,得到词的语义向量表示;其次,根据词语义向量表示,计算词之间的语义相似度;然后,选取与查询中词汇的语义最相似的词作为查询的扩展词,扩展原始查询语句;最后,基于提出的查询扩展方法构建了生物医学文档检索系统,针对基于维基百科或WordNet的传统查询扩展方法和BioASQ 2014—2015参加竞赛的系统进行对比实验和显著性差异指标分析。实验结果表明,基于语义向量表示查询扩展的检索方法所得到结果优于传统查询扩展方法的结果,平均准确率至少提高了1个百分点,在与竞赛系统的对比中,系统的效果均有显著性提高。     

支持基于内容检索的媒体语义特征分析平台*

以媒体信息服务的应用需求为牵引,研制开发了支持基于内容检索的媒体语义特征分析平台。该平台重点研究数字媒体语义对象的提取与检索、分类与标注和语义关联分析等关键技术,对平台的实施方案及其涉及到的关键技术进行了详细阐述,并对平台进行了具体实现。