Narrow Results

We developed a check reading system, termed INTERCHEQUE, which recognizes both the legal (LAR) and the courtesy amount (CAR) on bank checks. The version presented here is designed for the recognition of French, omni-bank, omni-scriptor, handwritten bank checks, and meets industrial requirements, such as high processing speed, robustness, and extremely low error rates.

We give an overview of our recognition system and discuss some of the pattern recognition techniques used. We also describe an installation which processes of the order of 70,000 checks per day. Results on a data base of about 170,000 checks show a recognition rate of about 75% for an error rate of the order of 1/10,000 checks.

Tibetan ancient literature is an important literature material for the study of ancient Tibetan culture, history, and the development of Sino Tibetan language family. However, the lack of work on ancient Tibetan word segmentation tools seriously restricts the research of ancient Tibetan literature. In view of this situation, this paper first utilizes ancient Tibetan interlaced contrast tagging data to extract the ancient Tibetan word segmentation dataset. Based on this dataset, we conduct numerous experiments for the task of ancient Tibetan word segmentation. Experimental results show that BiLSTM + CRF word segmentation algorithm can achieve the best performance, and the performance of ancient Tibetan word segmentation can be further improved through model ensemble. And the results show that the unknown words, insufficient training data and word ambiguity restrict the performance of ancient Tibetan word segmentation.

First, we compared nine machine learning methods and found out the methods applicable to the text analysis of the four arithmetic application questions. Then these methods were used to design and test the system. According to the test results of this study, logistic regression is the most suitable machine learning method for the text analysis of four arithmetic applications. The problem-solving system of research and development could reach the problem-solving rate of 76.5%.

We developed a check reading system, termed INTERCHEQUE, which recognizes both the legal (LAR) and the courtesy amount (CAR) on bank checks. The version presented here is designed for the recognition of French, omni-bank, omni-scriptor, handwritten bank checks, and meets industrial requirements, such as high processing speed, robustness, and extremely low error rates.

We give an overview of our recognition system and discuss some of the pattern recognition techniques used. We also describe an installation which processes of the order of 70,000 checks per day. Results on a data base of about 170,000 checks show a recognition rate of about 75% for an error rate of the order of 1/10,000 checks.

Uygur language is an agglutinative language with words as its basic unit. Because of the different positions in the word, the letters have different writing deformation. This paper analyzes the current two concepts of Uygur handwriting recognition, discusses the advantages and disadvantages of the two concepts, proposes an effective method of segmenting first and then recognizing, and establishes preliminary models for the post processing.

In order to help producers improve the quality of products and service provider higher quality services, a research on the feature and sentiment orientation mining of product review is necessary. In this paper, we introduce tasks that relate to the problem of product review sentiment classification and point out the main task of which is finding the sentiment orientation of a review is positive or negative. We propose a client perception based product feature mining algorithm using the sentiment analysis technology and realize the semantic analysis, dynamic extraction and general information mining on the product features and sentiment orientation. The feature and sentiment orientation of products are sorted by the weight of user interest, which helps customers access the conclusive review orientation more effectively. The experiment is based on real product review corpus downloaded from the internet, and it proved the effectiveness of the approach.

This paper research on construct an ontology to support the knowledge framework of “Network Operating System”, add implicit knowledge point relationship and use this ontology to implement a learning assistant system. We use ICTCLAS Chinese word segmentation to help domain-specific term extraction. Seven-step method is used to build course domain ontology, then add properties and characteristics to ontology, so computer can get and analyze the implicit relationships in knowledge. Then, we construct a learning assistant system based on the ontology we build, deal with the message user submit and parse out knowledge points relevant to it. Gain leading and follow-up knowledge point lists through ontology search. Set mapping file between course domain ontology and course sources in linked data way, helping achieve the convert from knowledge points to course sources, and helpful information will be displayed in system interface.