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。     

Eye movements of young and older adults during reading.

The eye movements of young and older adults were tracked as they read sentences varying in syntactic complexity. In Experiment 1, cleft object and object relative clause sentences were more difficult to process than cleft subject and subject relative clause sentences; however, older adults made many more regressions, resulting in increased regression path fixation times and total fixation times, than young adults while processing cleft object and object relative clause sentences. In Experiment 2, older adults experienced more difficulty than young adults while reading cleft and relative clause sentences with temporary syntactic ambiguities created by deleting the that complementizers. Regression analyses indicated that readers with smaller working memories need more regressions and longer fixation times to process cleft object and object relative clause sentences. These results suggest that age-associated declines in working memory do affect syntactic processing. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

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.     

Production and properties of micro‐porous glas bubble zinc and aluminium composites

Micro‐porous syntactic foams were produced by means of integration of glass bubbles into aluminium and zinc matrices. Preforms of glass bubbles were pressure infiltrated with the alloys AlSi9Cu9 ans ZnAl4Cu using squeeze casting. The preforms were sintered thermically without the use of bonding agents. Using the combination of different sintering steps syntactic foams with locally different densities could be produced. The mechanical properties of the foams were tested indicating a high compression strength of the foams and a very good compression energy absorption. Furthermore, corrosion behaviour and behaviour at higher temperatures were investigated.     

科技论文摘要英译策略研究——以《中国钨业》摘要英译为例

科技论文摘要属典型的信息类语篇,其英译的预期功能是向译文读者传播科研成果。译者应在充分了解汉英两种语言在语用、逻辑和句法差异的基础上,灵活进行相应的变通,使译文做到语言通顺自然、逻辑层次清楚、措辞精确严谨。     

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。     

复合泡沫塑料的性能改进研究

为改善复合泡沫塑料的介电性能,采用金属氧化物粒子填充改性双马来酰亚胺空芯玻璃微球复合泡沫塑料得到了高介电常数、低介质损耗因数、低密度、力学性能良好的电介质材料。     

观点句中评价对象/属性的缺省项识别方法研究

在多对象、多属性的评论文本中,评价对象和评价属性的缺省识别对于观点挖掘有着重要的作用。针对情感观点句中评价对象和评价属性的缺省问题,该文提出一种有效的缺省项识别方法。首先构造缺省项识别规则集,用于获取待识别的缺省项侯选集;将缺省项识别问题看作一个二元分类问题,选用词法和依存句法作为特征,使用决策树分类算法C4.5训练分类器模型,在测试集上对待识别的缺省项进行判别。实验结果表明,使用依存句法特征集分类的F值优于词法特征集约2%。将词法和依存句法两类特征融合与单类特征相比,分类精确率和F值分别提高了10%和5%左右,说明词法特征和依存句法特征的融合有利于缺省项识别。