1998 Volume 12 Issue 2
Published: 15 April 1998
-
Select all|
-
Review1998, 12(2): 2-8.This article discussed different kinds areas and techniques of signature information ext raction f rom Chinese text . with examples of news corpura ,scientific papers and document s ,it analysed areas and techniques of signature information ext raction f rom these text sand set some applicable production rules for scientific papers. The method and conclusion in this article are referernce for researchers on automatic indexing of texts ,automatic classification oftext s and automatic abst raction of texts.
-
Review1998, 12(2): 9-17.First , the paper int roduces the research situation and problem of automatic abstracting ,then gives general model of computer automatic abst racting ,at last ,int roduces the principles and methods of two kinds of automatic abst racting of our research , and their experimental results
-
Review1998, 12(2): 18-25.This paper declares the necessity of the processing of the multilingual information and the problems that must be solved in building a multilingual processing system ,Furthermore , it discusses the designation element s and developing method of a multilingual system software - “Global Envoy”, This system uses the ”Goal - Oriented Dynamic coding”technology ,which was invented by HCII. So it can solve all the problems of multilingual I/ O and the overlaps among the different coding method.
-
Review1998, 12(2): 26-31.Until now , there is no method which can effectively ext ract characters overlapping position lines ( i. e , preprinted f rames) . This paper considers the case that the characters are handwritten numerals , and proposes a new ext raction method. This method consist s of two steps - coarse processing and fine processing. The first step removes the position lines in order to obtain st ructure feature point s by using mathematical morphology operation.The second step reconst ruct s broken character by considering numeral st ructure features ,and removes redundant st rokes through some st roke smoothing algorithm ,At last ,the above method is applied to the recognition problem of Chinese bank check.
-
Review1998, 12(2): 32-37.This paper takes model match and t rigrams analysis methods as a starting point , applying tag set analysis method to the problem of Chinese text collation. A hybrid method for Chinese text collation is presented and it s performance improvement s are demonst rated..
-
Review1998, 12(2): 38-44.Transcription f rom PIN YIN to Chinese characters is an imporant field of Chinese information processing and the kernel of Chinese input systems , In this paper , the knowledge supporting , automatic word segmentation and replacing words on-line techniques were discussed. The intelligent approach based on statistic and rule method was presented and analyzed
-
Review1998, 12(2): 45-54.This paper discusses the design and implementation of an automatic pinyin -tagging system for the famous Song poems ,which amount s to 1. 6 million Chinese characters.The resource of the system includes : copora , knowledge base and information base. The automatic pinyin2tagging st rategies include : conditional probability strategy , mutual information st rategy and rule st rategy. The characteristic of the system is to combine the contemporary probabilistic language model with the phonological characteristics of the ancient poems in the process of automatic pinyin - tagging of Song poems. The experimental result is satisfying.
-
Review1998, 12(2): 55-63.In this paper , problem of semantic ambiguities is first discussed , and then several approaches are proposed. These approaches have all been used in TJ TITR German -Chinese Machine Translation System , and are proved to be a way to improve the efficiency of the system perfectly.
