Yongcheng Wang

Multiple documents summarization based on genetic algorithm

With the increasing volume of online information, it is more important to automatically extract the core content from lots of information sources. We propose a model for multiple documents summarization that maximize the coverage of topics and minimize the redundancy of contents. Based on Chinese concept lexicon and corpus, the proposed model can analyze the topic of each document, their relationships and the central theme of the collection to evaluate sentences. We present different approaches to determine which sentences are appropriate for the extraction on the basis of sentences weight and their relevance from the related documents. A genetic algorithm is designed to improve the quality of the summarization. The experimental results indicate that it is useful and effective to improve the quality of multiple documents summarization using genetic algorithm.

Chinese word sense disambiguation using hownet

Word sense disambiguation plays an important role in natural language processing, such as information retrieval, text summarization, machine translation etc. This paper proposes a corpus-based Chinese word sense disambiguation approach using HowNet. The method is based on the co-occurrence frequency between the relatives (such as synonym, antonymy, meronymy) of target word and each word in the context. Further, domains have been used to characterize the senses of polysemous word. To our knowledge, this is the first time a Chinese word sense disambiguation method using domain knowledge is reported. The accuracy is 73.2% at present. The experimental result shows that the method is very promising for Chinese word sense disambiguation.

A new model of document structure analysis

The purpose of document structure analysis is to get the document structure of the source text. Document structure is defined as 3 layers in the paper. A new model of document structure analysis — DLM is proposed. The model is composed of three layers: physical structure layer, logical structure layer and semantic structure layer, which are corresponding to the definition of the document structure. The input, output and operation of each layer are illustrated in details in the paper. The model has the feature of flexible, systematic and extendible. DLM is implemented on the Automatic Summarization System. It shows that the model is feasible and good result can be achieved.

Construction of mathematic model for automatic summarization

Automatic summarization is need of the era. Mathematical method can help logic analysis. However, there is no any previous study about mathematic description of automatic summarization. A mathematic model of automatic summarization is established and discussed in the paper. The model makes use of meta-knowledge to describe the composition of summary and help to calculate the semantic distance between summary and source document. It is proposed that how to get meta-knowledge aggregate and their weight are the key problems in the model. There is also a discussion of how to select output summary in the paper. The mathematic description of automatic summarization is useful for the application of automatic summarization and automatic assessment for summaries. An experiment and results are described in the paper to explain the application of mathematic model in details.

A mathematic model for automatic summarization

Automatic Summarization is need of the era. Mathematics is an important tool of nonfigurative thinking. A mathematic model of automatic summarization is established and discussed in the paper. The model makes use of meta-knowledge to describe the composition of the summary and help to calculate the semantic distance between summary and source document. It is proposed that how to get meta-knowledge aggregate and their weight are the key problems in the model.

Authorship analysis based on metrics

Summary form only given, as follows. Authorship analysis is to identify the authors of texts by genre, attributions, features and traits that are unique for a particular author. Another related issue of authorship analysis is to discriminate two authors by the distinguishing characteristic of authors. The computational linguistics will be divided into two layers. The bottom layer is interested in lexical information, stylistics and terminology in text and the upper layer is about structure and layout of text.Stylistic features and terminology statistics is concern with words and their pattern in particular corpus. The linguistic measures of bottom layer contain morpheme, average word length distributions, vocabulary distribution,word frequency, words order, average sentence length and sentence structure.The upper layer analysis does not only treats text as ?bag of words?? or ?set of words?. Furthermore, it contains not only structure and layout of text but also the uses and distribution of the various punctuation marks. The measures of texstructure contain the average paragraph length,the average section and chapter length, the uses and distribution of subtitles. Vocabulary richness of text is measured by word spectrum of a text and the weighted use of each vocabulary.