Graph-based Lexicalized Reordering Models for Statistical Machine Translation

Lexicalized reordering models are very important components of phrasebased translation systems.By examining the reordering relationships between adjacent phrases,conventional methods learn these models from the word aligned bilingual corpus,while ignoring the effect of the number of adjacent bilingual phrases.In this paper,we propose a method to take the number of adjacent phrases into account for better estimation of reordering models.Instead of just checking whether there is one phrase adjacent to a given phrase,our method firstly uses a compact structure named reordering graph to represent all phrase segmentations of a parallel sentence,then the effect of the adjacent phrase number can be quantified in a forward-backward fashion,and finally incorporated into the estimation of reordering models.Experimental results on the NIST Chinese-English and WMT French-Spanish data sets show that our approach significantly outperforms the baseline method.

WEB-BASED VIRTUAL CNC MACHINE MODELING AND OPERATION

A CNC simulation system based on intemet for operation training of manufacturing facility and manufacturing process simulation is proposed. Firstly, the system framework and a rapid modeling method of CNC machine tool are studied under the virtual environment based on PolyTrans and CAD software. Then, a new method is proposed to enhance and expand the interactive ability of virtual reality modeling language（VRML） by attaining communication among VRML, JavaApplet, JavaScript and Html so as to realize the virtual operation for CNC machine tool. Moreover, the algorithm of material removed simulation based on VRML Z-map is presented. The advantages of this algorithm include less memory requirement and much higher computation. Lastly, the CNC milling machine is taken as an illustrative example for the prototype development in order to validate the feasibility of the proposed approach.

Improving Parallel Corpus Quality for Chinese-Vietnamese Statistical Machine Translation

The performance of a machine translation system heavily depends on the quantity and quality of the bilingual language resource. However,getting a parallel corpus,which has a large scale and is of high quality,is a very difficult task especially for low resource languages such as Chinese-Vietnamese. Fortunately,multilingual user generated contents（ UGC）,such as bilingual movie subtitles,provide us access to automatic construction of the parallel corpus. Although the amount of UGC parallel corpora can be considerable,the original corpus is not suitable for statistical machine translation（ SMT） systems. The corpus may contain translation errors,sentence mismatching,free translations,etc. To improve the quality of the bilingual corpus for SMT systems,three filtering methods are proposed： sentence length difference,the semantic of sentence pairs,and machine learning. Experiments are conducted on the Chinese to Vietnamese translation corpus.Experimental results demonstrate that all the three methods effectively improve the corpus quality,and the machine translation performance（ BLEU score） can be improved by 1. 32.

Heidegger’s Metaphysics,a Theory of Human Perception:Neuroscience Anticipated,Thesis of Violent Man,Doctrine of the Logos

In this essay,our goal is to discover science in Martin Heidegger’s Introduction to Metaphysics,lecture notes for his 1935 summer semester course,because,after all,his subject is metaphysica generalis,or ontology,and this could be construed as a theory of the human brain.Here,by means of verbatim quotes from his text,we attempt to show that indeed these lectures can be viewed as suggestion for an objective scientific theory of human perception,the human capacity for deciphering phenomena,i.e.hermeneutics in its broadest sense.His added notes from the 1953 edition,all of which are comments,not corrections,imply that he never abandoned these thoughts on metaphysics,despite all of his utterances about a need to overcome it,and their popular interpretations to that effect.In his presentation,he further develops the colorful and intuitive style,an hermeneutic language,that he had created in his earlier work Being and Time.The logical functions of Dasein’s anatomical brain are performed by the logos machine,formerly the human soul,using top-down processing based on a global context,the noumenal cosmos which humans maintain internally.Heidegger’s 1942/43 winter semester lectures Parmenides extend in unbroken fashion his 1935 work,proving that he never abandoned,as is widely claimed,his metaphysical avenue of thought.