A Structured Prediction Approach for Statistical Machine Translation

We propose a new formally syntax-based method for statistical machine translation. Transductions between parsing trees are transformed into a problem of sequence tagging, which is then tackled by a search- based structured prediction method. This allows us to automatically acquire transla- tion knowledge from a parallel corpus without the need of complex linguistic parsing. This method can achieve compa- rable results with phrase-based method (like Pharaoh), however, only about ten percent number of translation table is used. Experiments show that the structured pre- diction approach for SMT is promising for its strong ability at combining words.

针对特定几何语言的句法语义一体化分析方法

提出了一种句法语义一体化的语言分析方法,句法分析和语义理解时采用并行方法,利用两者之间的相互关系实现句法和语义的分析。针对自然语言理解在几何特定领域的约束性,以依存语法为基础,利用标注过的语料库知识,采用规则统计模型,对已经标注好词性语义的句子词串进行句法语义一体化分析,生成符合数学规范的数学表达式。实验证明,建立的系统对100个几何描述的句子进行测试,得到的正确率为98％,在几何领域具有良好的实用性,能够满足实际的需要。

一个用于机器人自然语言理解的英语句法分析系统

在低挡微机中速度较慢的串行处理硬设备条件下，利用本文提出的启发式概念，分层搜索和匹配策略以及设置最大搜索长度等方法，可使推理速度提高一个数量级以上．此外，通过引入语义信息，分阶段消除歧义，自顶向下与自底向上相结合，以及把一般疑问句一律变成相应陈述句的方法，解决了自动英语句法分析中的一系列难题，缩小了知识库的规模。

一个数控自动编程系统的自然语言接口

本文简要介绍了一个数控自动编程专家系统的自然语言接口的实现.该自然语言接口是以我们研制的数控自动编程专家系统为背景,运行在 SUN3/4 工作站的 UNIX 下和 IBM/AT 机的 DOS 下,用 C语言编程.该自然语言接口由词法分析、句法分析、语义语用分析、目标生成和图形仿真五个模块及相应的知识库构成.该接口能够接受数控编程系统所需的对工件的英语自然语言描述并处理一些比较简单的英语语言现象.

基于IDEF&UML的生产过程管理系统的建模研究

提出了IDEF与UML两者结合的系统建模方法,能够有效地避免IDEF对信息过程流建模和UML语义描述精确性及使用灵活性的不足.该方法采用IDEF0进行系统功能建模,用IDEF1x和UML模型进行信息建模和面向对象的软件系统设计.用该方法设计的沈阳某冶金设备有限公司的基于组件的生产过程管理系统模型具有良好的维护性、可扩展性和重用性,证明了该方法的可行性.

金钱启动与道德的关系及道德认同的调节

In this article, we begin from the research about how money influences the behavior of people, and try to discuss how money influences people's moral judgment on the five degrees of morality (harm/care, fairness/reciprocal, loyalty/in-group, authority/respect, purity/sanctity). Meanwhile, we try to discuss whether the money priming is based on the mechanism of competition priming. Besides that, we want to find out whether moral identification and positive vocabulary could rescue the change of moral judgment after money priming. The money priming in this research is based on picture priming and syntax priming; the competition priming and moral identification priming are based on imagination priming. We chose the undergraduate, graduate student and adult as sample, combined the scale investigation with computer based experiment. This research contains five standard case experiments, which form three. Based on all the research above, we have some conclusions: 1. Money priming has impacts on moral judgment, which are not consistent on different degree of morality. But the total effect of money priming is that it changes moral judgment to a worse state. 2. Money priming is not complete competition priming, but social value orientation (including competition orientation) could mediate the influence of money priming on moral judgment. Generally, people with personal orientation or competition orientation could be influenced more easily by money priming. 3. After money priming, the moral judgment could be influence by moral identification and positive vocabulary. In all, both the moral judgment and positive vocabulary could make the moral judgment to a better state. But the function of them may be different, moral identification is more related to moral cognition and positive vocabulary is more related to moral emotional regulation. This research is based on priming method, and supports the money influence on psychology, the concept of morality and moral identification with experimental evidence. Also this research discusses the measurement of morality.

语句句法成分边界和韵律特征知觉

The research investigates the acoustic-phonetic correlates of various levels of syntactic boundaries and the perception of prosody in Mandarin Chinese, more specifically, the way speakers express the syntatic relations between sentence compounents and teh perceptual representations of prosody. The relation between phonology and syntax in Chinese language is studied by comparing the perceptual representations and syntactic structures of sentences. The results may have theoretical and practical implications for research in fields of speech perception, linguistics and psycholinguistics, and for the development of speech engineering in China.