Chinese word segmentation is a key technology for automatic summarization. Whether the segmentation is successful and has no ambiguity or not will directly affect sentence weight calculation. In the segmentation process, the structure of word segmentation dictionary is particularly important. A rational structure of a word segmentation dictionary can improve the segmentation process of the dictionary query speed, and, thus, improves the efficiency of Chinese word segmentation. This paper is based on the dictionary of Hash structure. In this paper, the authors adopt the prefix and suffix query approach to build word segmentation dictionary, combined with an improved Chinese word segmentation algorithm for maximum matching to improve the segmentation efficiency and accuracy.

The prefix and suffix query of Chinese word segmentation algorithm for maximum matching

In order to improve the speed of Chinese full-text retrieval in the premise of ensuring Chinese ambiguity inclusion and length limitation, this paper introduces the application methods of Chinese full-text retrieval system and the current application situation of Chinese word segmentation technology. Based on the existed word segmentation algorithms, this paper proposed an improved Chinese word segmentation algorithm. In the proposed method, the procedure of indexing is to construct the map between the relative words in the context and the dictionary. This paper improves the diction to realize better mapping with relative words, so as to realize Chinese words segmentation. The experiments demonstrate that the proposed Chinese full-text words segmentation algorithm is more effective than the existing methods.

Research on Words Segmentation Technology in Chinese Full Text Retrieval System

With the rapid development of information technology, knowledge graph extracts more and more attentions from researchers. However, Chinese knowledge graph of construction industry is still at the beginning stage, and Chinese word segmentation method, as the basis of natural language processing, plays a vital role on the process of building knowledge graph. In this paper, we study Chinese design specifications of building stairs, and proposes a reverse maximum matching (RMM) based word segmentation method to parse Chinese building specifications. The proposed method first converts the dictionary of building into a hash dictionary. And then, by traversing the design specifications of building stairs, the proposed method handles the non-Chinese symbols in the design specifications. Finally, the proposed method uses RMM algorithm to match contexts with Chinese design specifications and generate the goal results. Through performing experiments on Chinese design specifications of building stairs, the results can be shown that the proposed method is feasible.

A RMM Based Word Segmentation Method for Chinese Design Specifications of Building Stairs

The project reserve of power grid enterprises is related to the company’s future development focus and the creation of key products, and is a key step in the construction and development of enterprises. However, due to the large amount of project data in the reserve stage, the data sorting, screening, and value evaluation of the reserve project are huge, and the human processing is time-consuming and labor-intensive. Therefore, it is urgent to study the intelligent processing of enterprise reserve project data based on artificial intelligence technology to improve the quality and efficiency of enterprise reserve project management. Aiming at the needs of intelligent evaluation of enterprise project data value, this paper studies the reserve project clustering algorithm based on improved k-means algorithm technology, and realizes the automatic classification of project types, thereby improving the management efficiency of reserve projects.

Research on Intelligent Management Technology of Project Reserve Data in Enterprise Digital Transformation

This paper designs Intelligent Question Answering System (IQAS) by a combined use of the concept of ontology and search engine. The system can help users to obtain more accurate answers. It raises the issue of user word segmentation and keyword extraction, and searches keyword-related information on the web, and then returns results and saves them to the database, which enables users to extract easily. It is found through the search that the results are more accurate than those before, and the users have more choices.

Study of Intelligent Question Answering System Based on Ontology

Chinese word segmentation is a basic research issue on Chinese information processing tasks.And Chinese word segmentation is a very important component in many field of Chinese information process.The paper proposes an unsupervised training method for acquiring probability models that accurately segment Chinese character sequences into words.Then it presents a detailed analysis of the two great dificulties in word segmentation.And finally,it points out the research problems to be resolved on Chinese word segmentation.

Liu Yan-ji

Papers

State of the art and difficulties in Chinese word segmentation technology