基于桥连接的词典学习方法的语义解析

现阶段的语义解析方法大部分都基于组合语义,这类方法的核心就是词典。词典是词汇的集合,词汇定义了自然语言句子中词语到知识库本体中谓词的映射。语义解析一直面临着词典中词汇覆盖度不够的问题。针对此问题,该文在现有工作的基础上,提出了基于桥连接的词典学习方法,该方法能够在训练中自动引入新的词汇并加以学习,为了进一步提高新学习到的词汇的准确度,该文设计了新的词语—二元谓词的特征模板,并使用基于投票机制的核心词典获取方法。该文在两个公开数据集(WebQuestions和Free917)上进行了对比实验,实验结果表明,该文方法能够学习到新的词汇,提高词汇的覆盖度,进而提升语义解析系统的性能,特别是召回率。     

A practical minimum distance method for syntax error handling

We present a method for recovering from syntax errors encountered during parsing. The method provides a form of minimum distance repair, has linear time complexity, and is completely automatic. A formal method is presented for evaluating the performance of error recovery methods, based on global minimum-distance error correction. The minimum-distance error recovery method achieves a theoretically best performance on 80% of Pascal programs in the weighted Ripley-Druseikis collection. Comparisons of performance with other error recovery methods are given.     

Interference effects from grammatically unavailable constituents during sentence processing.

Evidence from 3 experiments reveals interference effects from structural relationships that are inconsistent with any grammatical parse of the perceived input. Processing disruption was observed when items occurring between a head and a dependent overlapped with either (or both) syntactic or semantic features of the dependent. Effects of syntactic interference occur in the earliest online measures in the region where the retrieval of a long-distance dependent occurs. Semantic interference effects occur in later online measures at the end of the sentence. Both effects endure in offline comprehension measures, suggesting that interfering items participate in incorrect interpretations that resist reanalysis. The data are discussed in terms of a cue-based retrieval account of parsing, which reconciles the fact that the parser must violate the grammar in order for these interference effects to occur. Broader implications of this research indicate a need for a precise specification of the interface between the parsing mechanism and the memory system that supports language comprehension. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Error handling in a parallel LR substring parser

Parallel parsing is currently receiving attention but there is little discussion about the adaptation of sequential error handling techniques to these parallel algorithms. We describe a noncorrecting error handler implemented with a parallel LR substring parser. The parser used is a parallel version of Cormack's LR substring parser. The applicability of noncorrecting error handling for parallel parsing is discussed. The error information provided for a standard set of 118 erroneous Pascal programs is analysed. The programs are run on the sequential LR substring parser.     

基于启发式搜索与预标注的中文CCG句法分析

针对中文组合范畴语法(CCG)分析困难的特点,研究如何将两种彼此相互独立的技术共同应用在中文CCG句法分析上。首先使用预标注算法,使用对数线性模型通过去除那些概率较低的词汇范畴来对句子的潜在分析空间进行剪枝。然后应用启发式搜索算法进一步加速分析过程。最后从时间效率和分析精度两个维度对所使用的方法进行验证。实验表明,基于启发式搜索与预标注的句法分析算法可以显著地提高分析效率与分析精度。     

基于SVM的汉语句子片段划分

针对长句子引起句法分析性能下降的问题,本文提出了一种基于SVM的句子片段划分方法:先根据语法结构将句子划分为多个片段,识别出每个片段的类别;然后根据片段的类别将句子分割为几个部分,每个部分作为句法分析的基本单元;最后将句法分析之后的各个部分进行合并,形成完整的分析结果.该方法减小了句法分析的复杂度,提高了分析的准确率.     

Building a Language‐Independent Discourse Parser using Universal Networking Language

Discourse parsing has become an inevitable task to process information in the natural language processing arena. Parsing complex discourse structures beyond the sentence level is a significant challenge. This article proposes a discourse parser that constructs rhetorical structure (RS) trees to identify such complex discourse structures. Unlike previous parsers that construct RS trees using lexical features, syntactic features and cue phrases, the proposed discourse parser constructs RS trees using high‐level semantic features inherited from the Universal Networking Language (UNL). The UNL also adds a language‐independent quality to the parser, because the UNL represents texts in a language‐independent manner. The parser uses a naive Bayes probabilistic classifier to label discourse relations. It has been tested using 500 Tamil‐language documents and the Rhetorical Structure Theory Discourse Treebank, which comprises 21 English‐language documents. The performance of the naive Bayes classifier has been compared with that of the support vector machine (SVM) classifier, which has been used in the earlier approaches to build a discourse parser. It is seen that the naive Bayes probabilistic classifier is better suited for discourse relation labeling when compared with the SVM classifier, in terms of training time, testing time, and accuracy.     

Excel财务函数应用解析

在Excel财务函数对一般的财务计算,如确定贷款的支付额、投资的未来值或净现值,以及债券或息票的价值等非常方便。本文主要介绍投资计算函数、折旧计算函数、偿还率计算函数、债券及其他金融函数等典型财务函数。     

Static virtualization of C source code

Many existing systems are written in C and are not re‐entrant or thread safe. Sometimes these systems are required in a context for which they were not first designed, possibly meaning they now need to be re‐entrant. This article introduces a program that filters C source code, modifying shared resources (the global variables) to make the code re‐entrant: ‘virtualizing’ the code. The code is then compiled as normal. This approach allows programmatic virtualization with little cost at runtime. Copyright © 2007 John Wiley & Sons, Ltd.     

受限领域问答系统的中文问句分析研究

对用户所提问句的理解是受限领域问答系统实现的关键,该文提出一种基于本体和问句句型模板规则的中文问句分析方法,研究如何使用问句语义表征来表示问句分析的结果,将该方法应用于某受限领域问答系统中。实验结果表明,使用该方法进行中文问句分析,准确率达90%以上,可以在实际的问答系统中使用该方法。