Inter-operability and reusability: the science of annotation

Annotating linguistic data has become a major field of interest, both for supplying the necessary data for machine learning approaches to NLP applications, and as a research issue in its own right. This comprises issues of technical formats, tools, and methodologies of annotation. We provide a brief overview of these notions and then introduce the papers assembled in this special issue.     

Not all arguments are processed equally: a distributional model of argument complexity

Language Resources and Evaluation - This work addresses some questions about language processing: what does it mean that natural language sentences are semantically complex? What semantic features...     

A robust web personal name information extraction system

Personal information extraction, which extracts the persons in question and their related information (such as biographical information and occupation) from web, is an important component to construct social network (a kind of semantic web). For this practical task, two important issues are to be discussed: personal named entity ambiguity and the extraction of personal information for a specific person. For personal named entity ambiguity, which is a common phenomenon in the fast growing web resource, we propose a robust system which extracts lightweight features with a totally unsupervised approach from broad resources. The experiments show that these lightweight features not only improve the performances, but also increase the robustness of a disambiguation system. To extract the information of the focus person, an integrated system is introduced, which is able to effectively re-use and combine current well-developed tools for web data, and at the same time, to identify the expression properties of web data. We show that our flexible extraction system achieves state-of-the-art performances, especially the high precision, which is very important for real applications.     

Multi-Domain Sentiment Classification with Classifier Combination

State-of-the-arts studies on sentiment classification are typically domain-dependent and domain-restricted.In this paper,we aim to reduce domain dependency and improve overall performance simultaneously by proposing an efficient multi-domain sentiment classification algorithm.Our method employs the approach of multiple classifier combination.In this approach,we first train single domain classifiers separately with domain specific data,and then combine the classifiers for the final decision.Our experiments show that this approach performs much better than both single domain classification approach(using the training data individually) and mixed domain classification approach(simply combining all the training data).In particular,classifier combination with weighted sum rule obtains an average error reduction of 27.6%over single domain classification.     

基于词边界分类的中文分词方法

该文研究和探讨一种新的分词方法 基于词边界分类的方法。该方法直接对字符与字符之间的边界进行分类,判断其是否为两个词之间的边界,从而达到分词的目的。相对于目前主流的基于字标注的分词方法,该方法的实现和训练更加快速、简单和直接,但却能获得比较接近的分词效果。更显著的是我们可以很容易地从词边界分类方法获得在线分词学习方法,该方法能够使我们的分词系统非常迅速地学习新的标注样本。     

Design,Synthesis, Molecular Docking Analysis and Biological Evaluations of 4-[(Quinolin-4-yl)amino]benzamide Derivatives as Novel Anti-Influenza Virus Agents

In this study, a series of 4-[(quinolin-4-yl)amino]benzamide derivatives as the novel anti-influenza agents were designed and synthesized. Cytotoxicity assay, cytopathic effect assay and plaque inhibition assay were performed to evaluate the anti-influenza virus A/WSN/33 (H1N1) activity of the target compounds. The target compound G07 demonstrated significant anti-influenza virus A/WSN/33 (H1N1) activity both in cytopathic effect assay (EC₅₀ = 11.38 ± 1.89 µM) and plaque inhibition assay (IC₅₀ = 0.23 ± 0.15 µM). G07 also exhibited significant anti-influenza virus activities against other three different influenza virus strains A/PR/8 (H1N1), A/HK/68 (H3N2) and influenza B virus. According to the result of ribonucleoprotein reconstitution assay, G07 could interact well with ribonucleoprotein with an inhibition rate of 80.65% at 100 µM. Furthermore, G07 exhibited significant activity target PA−PB1 subunit of RNA polymerase according to the PA−PB1 inhibitory activity prediction by the best pharmacophore Hypo1. In addition, G07 was well drug-likeness based on the results of Lipinski’s rule and ADMET prediction. All the results proved that 4-[(quinolin-4-yl)amino]benzamide derivatives could generate potential candidates in discovery of anti-influenza virus agents.     

Dynamic stability of stiffened laminated composite plates and shells subjected to in-plane pulsating forces

The dynamic stability of laminated composite stiffened or non-stiffened plates and shells due to periodic in-plane forces at boundaries is investigated in this paper. A three-dimensional (3-D) degenerated shell element and a 3-D degenerated curved beam element are used to model plates/shells and stiffeners, respectively. The characteristic equations to find the natural frequencies, buckling loads and their corresponding mode shapes are obtained from the finite element equation of motion. Then, the method of Hill's infinite determinants or the method of multiple scales is applied to analyse the dynamic instability regions. Numerical results are presented to demonstrate the effects of various parameters, such as skew angle, lamination scheme, stiffened scheme, in-plane force type and curvature of cylindrical shell, on the dynamic stability of stiffened and non-stiffened plates and shells subjected to in-plane pulsating forces at boundaries.     

中文词汇网络:跨语言知识处理基础架构的设计理念与实践

中文词汇网络(Chinese WordNet, 简称CWN)的设计理念,是在完整的知识系统下兼顾词义与词义关系的精确表达与语言科技应用。中文词义的区分与词义间关系的精确表征必须建立在语言学理论,特别是词汇语义学的基础上。而词义内容与词义关系的发掘与验证,则必须源自实际语料。我们采用的方法是分析与语料结合。结合的方式则除了验证与举例外,主要是在大量语料上平行进行词义标记,以反向回馈验证。完整、强健知识系统的建立,是兼顾知识本体(ontology)的完备规范(formal integrity)和人类语言系统内部的完整知识。我们采用了上层共享知识本体(SUMO)来提供知识的规范系统表征。