Chinese Information Processing Research Articles

Analysis and Evaluation of Text Comparison Based on Intelligent Optimization Algorithm

Text transcription is crucial in Chinese information processing. Text transcription has always existed since ancient times, but no matter whether it is manual transcription in ancient times or modern transcription using communication and storage devices, random errors cannot be avoided when a message has been forwarded and transcribed many times. In this paper, we study how to measure the size of differences between different versions of texts, how to estimate the number of transmissions experienced between two texts, and how to design an effective and fast algorithm for the calculation of the first two types of problems in the study of text transcription, with respect to the characteristics of text transcription. This paper proposes the concept of text similarity, constructs the TF-IDF similarity evaluation model of text, the text transmission evaluation model based on Gaussian process (i.e., GFCT Model), and the model based on the immune frog jumping algorithm to analyze the comparative processing of text, so as to achieve accurate and effective information processing, with a view to providing a new method for text data processing, and improving the accuracy and effectiveness of text data processing.

Research on Weibo New Word Recognition based on Weibo Data and Statistical Information

One of the key challenges in the field of Chinese information processing is the recognition of Weibo new words, which has a profound impact on machine translation and text classification. As Weibo has become the most used social platform for internet users, mining new vocabulary from Weibo data not only helps to deeply understand the data itself, but also provides personalized recommendation services for users. Although a large amount of research has focused on the recognition of Weibo new words, specialized research in this field is still scarce. In this article, we propose a Weibo new word recognition strategy that combines Weibo content features and statistical information. Firstly, extract repetitive vocabulary from Weibo topic names, and then use various methods such as absolute frequency, relative frequency, mutual information, and information entropy to filter for incorrect vocabulary. The experimental results show that by setting appropriate thresholds, incorrect vocabulary can be effectively filtered out, thereby improving recognition performance.

Human intelligence-based metaverse for co-learning of students and smart machines.

This paper proposes a Human Intelligence (HI)-based Computational Intelligence (CI) and Artificial Intelligence (AI) Fuzzy Markup Language (CI&AI-FML) Metaverse as an educational environment for co-learning of students and machines. The HI-based CI&AI-FML Metaverse is based on the spirit of the Heart Sutra that equips the environment with teaching principles and cognitive intelligence of ancient words of wisdom. There are four stages of the Metaverse: preparation and collection of learning data, data preprocessing, data analysis, and data evaluation. During the data preparation stage, the domain experts construct a learning dictionary with fuzzy concept sets describing different terms and concepts related to the course domains. Then, the students and teachers use the developed CI&AI-FML learning tools to interact with machines and learn together. Once the teachers prepare relevant material, students provide their inputs/texts representing their levels of understanding of the learned concepts. A Natural Language Processing (NLP) tool, Chinese Knowledge Information Processing (CKIP), is used to process data/text generated by students. A focus is put on speech tagging, word sense disambiguation, and named entity recognition. Following that, the quantitative and qualitative data analysis is performed. Finally, the students' learning progress, measured using progress metrics, is evaluated and analyzed. The experimental results reveal that the proposed HI-based CI&AI-FML Metaverse can foster students' motivation to learn and improve their performance. It has been shown in the case of young students studying Software Engineering and learning English.

Research on Computing Word Similarity in Pre-Qin Classics Language Network Oriented to Digital Humanities

At present, there is relatively little research on ancient Chinese texts in the field of digital humanities, and ancient Chinese information processing urgently needs new algorithms. To realize the word similarity calculation of pre-Qin classics, a total of 25 pre-Qin classics were first mapped into a language network. Based on local relative entropy, we proposed an improved weighted network node similarity calculation method (LREW). This method judges the similarity based on the local network characteristics of the nodes, and the degree of the nodes and the weight information of the edges between the nodes are considered. We used the relative entropy to calculate the difference in the amount of information between different nodes. After experimental comparison, compared with the existing LRE and RE algorithms based on relative entropy, the proposed LREW method can achieve the best results in calculating the similarity between words in the pre-Qin classics. Compared with CN, Jaccard, Salton, and CDSim algorithms based on common neighbor nodes, although the accuracy of LREW is low, the comprehensiveness of the similar word recognition is high, which can ensure that potential similar nodes in the network will not be missed.

The Power of Digitalization in the Life Sciences and Diagnostics Sectors with art image enhancement

The traditional image enhancement processing method is limited by the contrast between image background and enhancement object when processing, which leads to poor image enhancement processing effect and low processing efficiency. With the development of technology, the application of digital electronics is expanding. In order to solve the above problems, the application of digital electronics in image enhancement is explored by studying the method of Chinese character art image enhancement based on digital electronics. Digital coding and Chinese character information processing of Chinese character art images using digital electronics. Retinex enhancement algorithm is improved by using PLIP model to realize Chinese character art image enhancement process. The simulation results demonstrate that the studied image enhancement method can effectively improve the processing efficiency by about 50%, and the image enhancement process is more effective.

Research and Implementation of Chinese Automatic Word Segmentation System Based on Complex Network Features

In the field of Chinese information processing, automatic word segmentation is a fundamental concept. Complex networks are widely used in modeling and analysis of complex systems across a wide range of disciplines, prompting an increase in interest in the structure of complex networks and the relationship between structure and function among academics. In contrast to Western countries, while there is a syllabic change in spoken Chinese that has formed a degree of boundary, it appears in writing as continuous Chinese character strings with no obvious word segmentation marks and no morphological segmentation marks. In summary, an in-depth study of network news information processing through complex networks can provide effective means to purify the network environment and reduce massive waste of communication resources and users’ time, which is of significant research importance. The characteristics of complex networks are used to study the Chinese automatic word segmentation system in this paper. A new interdisciplinary subject, complex networks and complex systems, has emerged. Researchers from various disciplines are attempting to study complex systems through the lens of system complexity theory and complex network theory in order to better understand the mechanism of network fault diffusion.

Semantic Role Labeling Integrated with Multilevel Linguistic Cues and Bi-LSTM-CRF

Chinese Semantic Role Labeling (SRL) is the core technology of semantic understanding. In the field of Chinese information processing, where statistical machine learning is still the mainstream, the traditional labeling methods rely heavily on the parsing degree of syntax and semantics of sentences. Therefore, the labeling precision is limited and cannot meet the current needs. This paper adopts the model based on a bidirectional long short-term memory network combined with the Conditional Random Field (Bi-LSTM-CRF). In the feature processing stage, pooling technology is combined with sampling and selecting multifeature vector groups to improve the performance of the sequence labeling model. Lexical, syntactic, and other multilevel linguistic features are integrated into the training to realize in-depth improvement of the original labeling model. Through several groups of experiments, the precision of model annotation in this paper has been significantly improved combined with linguistic-assisted analysis, which proves that it can optimize the annotation performance of the model by integrating relevant linguistic features into the model based on Bi-LSTM-CRF and sampling and extracting multifeature groups; the evaluation of F increases to 82.18 percent.

OpenKG Chain: A Blockchain Infrastructure for Open Knowledge Graphs

Abstract The early concept of knowledge graph originates from the idea of the Semantic Web, which aims at using structured graphs to model the knowledge of the world and record the relationships that exist between things. Currently publishing knowledge bases as open data on the Web has gained significant attention. In China, CIPS(Chinese Information Processing Society) launched the OpenKG in 2015 to foster the development of Chinese Open Knowledge Graphs. Unlike existing open knowledge-based programs, OpenKG chain is envisioned as a blockchain-based open knowledge infrastructure. This article introduces the first attempt at the implementation of sharing knowledge graphs on OpenKG chain, a blockchain-based trust network. We have completed the test of the underlying blockchain platform, as well as the on-chain test of OpenKG's dataset and toolset sharing as well as fine-grained knowledge crowdsourcing at the triple level. We have also proposed novel definitions: K-Point and OpenKG Token, which can be considered as a measurement of knowledge value and user value. 1033 knowledge contributors have been involved in two months of testing on the blockchain, and the cumulative number of on-chain recordings triggered by real knowledge consumers has reached 550,000 with an average daily peak value of more than 10,000. For the first time, We have tested and realized on-chain sharing of knowledge at entity/triple granularity level. At present, all operations on the datasets and toolset in OpenKG.CN, as well as the triplets in OpenBase, are recorded on the chain, and corresponding value will also be generated and assigned in a trusted mode. Via this effort, OpenKG chain looks to provide a more credible and traceable knowledge-sharing platform for the knowledge graph community.

兼类词概率分布计量考察及语法搭配模式在中文信息处理中的应用

兼类词概率分布计量考察及语法搭配模式在中文信息处理中的应用

Chinese Language Information Processing Considering Efficient Decoding Algorithm for Phonetic Conversion

For Chinese language information processing system, it is a very typical 3C system, which integrates computer and communication into one. Connect smart devices through the application of various technologies, mainly including network transmission technology, audio and video technology, information processing technology, etc. and use a highly efficient management system to uniformly manage and control all devices. According to the actual situation of human communication, the most direct way is language communication. Dedicated voice recognition chips are mainly used to control and control smart devices in traditional smart home systems. The currently recognized voice recognition products usually rely on the Internet as an important means to improve their efficiency.

Discussion-record-based prediction model for creativity education using clustering methods

The development of creativity is a major challenge for engineering education. Creativity not only affects originality and innovation but also increases the utility of products and ideas, thus yielding a competitive advantage in the market. Although studies have demonstrated that creativity can be practically assessed through student innovation or responses to creativity questionnaires, few studies have explored how creativity is developed. Therefore, this study developed a model for predicting creativity based on the discussion records of students during creative activities. The model was designed using the Chinese Knowledge Information Processing tokenization system, a term frequency–inverse document frequency method, and support vector machines. The experimental results revealed a model accuracy of 93 %, thus demonstrating the model’s feasibility for predicting creativity. Furthermore, the students’ key terms were obtained by using k-means clustering with the proposed model, thus yielding valuable supplementary information for exploring the development of creative ideas. These results revealed that data mining has substantial value in creativity education. Therefore, the proposed predictive model is suitable for predicting creativity in learning activities based on discussion records. It can support teachers’ assessment of student performance and provision of timely guidance and feedback to enhance creative thinking and stimulate imagination among engineering students.

Chinese shallow semantic parsing based on multilevel linguistic clues

With rapid development of artificial intelligence and Chinese information processing technology, research related to natural language processing have reached the level of semantic understanding gradually, while Chinese Shallow Semantic Parsing is the key technique in the semantic understanding field. In this paper, a further improvement is conducted on the basic model of Chinese semantic role labeling for linear classification based on conditional random fields. In this paper, a method of combination of linguistic clues, combining with the existing linear sequence labeling algorithm and integrating some multilevel linguistic clues, such as morphology is related to syntax, in the model training to reconstruct and improve the Chinese semantic role labeling model of linear sequence. Through the experimental comparison and linguistic assistant analysis, this paper puts forward a targeted improvement method to significantly improve the accuracy of model labeling and proves that the integration of related linguistic clues in the semantic role labeling model based on linear sequence can improve the effect of model labeling.

Sentiment Analysis of Brand Personality Positioning Through Text Mining

This article uses text mining and a Chinese word segmentation program developed by the Chinese Knowledge and Information Processing Group in Taiwan's Academia Sinica to analyze Facebook posts from 14 e-commerce companies. In addition, a list of keywords representing brand personalities is analyzed to reveal key factors affecting which social media posts attract consumers' attention. This research uses statistical analysis with a nonmanual questionnaire that is efficient and based on computer science to provide a reference for businesses operating Facebook fan pages and internet marketing.

Response Selection and Automatic Message-Response Expansion in Retrieval-Based QA Systems using Semantic Dependency Pair Model

This article presents an approach to response selection and message-response (MR) database expansion from the unstructured data on the psychological consultation websites for a retrieval-based question answering (QA) system in a constrained domain for emotional support and comforting. First, we manually construct an initial MR database based on the articles collected from the psychological consultation websites. The Chinese Knowledge and Information Processing probabilistic context-free grammar is adopted to obtain the semantic dependency graphs (SDGs) of all the messages and responses in the initial MR database. For each sentence in the MR database, all the semantic dependencies, each composed of two words and their semantic relation, are extracted from the SDG of the sentence to form a semantic dependency set. Finally, a matrix with the element representing the correlation between the semantic dependencies of the messages and their corresponding responses is constructed as a semantic dependency pair model (SDPM) for response selection. Moreover, as the number of MR pairs in the psychological consultation websites is increasing day by day, the MR database in the QA system should be expanded to meet the needs of the users. For MR database expansion, the unstructured data from the message board are automatically collected. For the collected data, the supervised latent Dirichlet allocation is adopted for event detection and then the event-based delta Bayesian Information Criterion is used for message and response article segmentation. Each extracted message segment is then fed to the constructed retrieval-based QA system to find the best matched response segment and the matching score is also estimated to verify if the new MR pair is suitable to be included in the expanded MR database. Fivefold cross validation was employed to evaluate the performance of the proposed retrieval-based QA system over the expanded MR database based on SDPM. Compared to the vector space model-based method, the Okapi BM25 model, and the deep learning-based sequence-to-sequence with attention model, the proposed approach achieved a more favorable performance according to a statistical significance test. The retrieval accuracy based on MR expansion was also evaluated and a satisfactory result was obtained confirming the effectiveness of the expanded MR database. In addition, the user's satisfaction score of the proposed system was evaluated using the Cronbach's alpha value and the satisfaction score of the proposed SDPM was higher than those of the methods for comparison.

Research on Chinese Semantic Role Labeling Based on Binary Strategy

Chinese SRL(Semantic Role Labeling) is a cutting-edge technology in the field of Chinese information processing. Now it has become one of the hottest research areas in Chinese information processing research. In this paper, based on the analysis of the previous SRL theory, the Chinese SRL technology, the comparison of advantages and disadvantages, this paper classifies and discusses the basic algorithm ideas of Chinese SRL. At the same time, the thinking on the SRL system is formed and a Chinese SRL system based on the binary strategy is proposed. The system adopts a binary strategy SRL method, combined with a statistical method based on linear feature combination research, fusion of Chinese short-sentence analysis of the study, to achieve a binary strategy-based Chinese SRL system design and construction. Through the experimental comparison, it is proved that the SRL system based on the binary strategy has a good annotation effect.

A Query Algorithm for Heterogeneous Information Network

With the rapid growth of the scale of the graph data, the form of its organization is more complicated. Heterogeneous information network has become an important tool for management and mining of graph data. It has been widely used in Chinese information processing, learning community mining and online shopping. The accessibility problem of heterogeneous information network is the basic problem of its research. Based on the literature [1], this paper proposes a path-based reachability query algorithm based on query preference. The algorithm establishes the path pattern index by preprocessing step, and uses the query preference to update the above indexes to achieve better processing the purpose of online inquiries. The experiment proves the effectiveness of the proposed method.

Ontology-based GFML agent for patent technology requirement evaluation and recommendation

Patent technology requirement evaluation and recommendation are critical for patent strategy, patent management, and patent usage in an organization. This paper proposes a patent technology evaluation and recommendation agent based on a soft-computing approach to enhance patent expansibility and technology transfer. First, we investigate the relationship between patent technology and patent owners, such as academic institutes or organizations, and integrate the collected patent data with the characteristics of organizations to establish a popular patent ontology for general academic institutes or organizations. Then, the patent’s suitability for a specific organization is determined based on concepts extracted using Chinese Knowledge Information Processing. Next, we refer to the Japan Patent Office evaluation index and intellectual property quotient to describe the knowledge base and rule base of the patent quality evaluation agent by using fuzzy markup language (FML). A comprehensive patent quality evaluation mechanism is implemented, and the genetic algorithm is adopted to improve the performance of the proposed agent. Additionally, the patent requirement level evaluation mechanism infers the patent requirement level according to the basic information of an organization. Finally, we present a novel FML-based patent requirement recommendation agent to recommend a patent for an organization by considering the suitability of the patent technology for such an organization, the results of the comprehensive patent quality evaluation process, and the results of the evaluation of the demander’s patent requirements. According to the results, the proposed agent is feasible for patent recommendation. In the future, we will combine an intelligent robot with the GFML agent to assist humans or organizations in recommending an appropriate patent.

Spoken dialog summarization system with HAPPINESS/SUFFERING factor recognition

This work presents a spoken dialog summarization system with HAPPINESS/SUFFERING factor recognition. The semantic content is compressed and classified by factor categories from spoken dialog. The transcription of automatic speech recognition is then processed through Chinese Knowledge and Information Processing segmentation system. The proposed system also adopts the part-of-speech tags to effectively select and rank the keywords. Finally, the HAPPINESS/SUFFERING factor recognition is done by the proposed point-wise mutual information. Compared with the original method, the performance is improved by applying the significant scores of keywords. The experimental results show that the average precision rate for factor recognition in outside test can reach 73.5% which demonstrates the possibility and potential of the proposed system.

Detecting negation and scope in Chinese clinical notes using character and word embedding

Background and objectivesResearchers have developed effective methods to index free-text clinical notes into structured database, in which negation detection is a critical but challenging step. In Chinese clinical records, negation detection is particularly challenging because it may depend on upstream Chinese information processing components such as word segmentation [1]. Traditionally, negation detection was carried out mostly using rule-based methods, whose comprehensiveness and portability were usually limited. Our objectives in this paper are to: 1) Construct a large Chinese clinical notes corpus with negation annotated; 2) develop a negation detection tool for Chinese clinical notes; 3) evaluate the performance of character and word embedding features in Chinese clinical natural language processing. MethodsIn this paper, we construct a Chinese clinical corpus consisting of admission and discharge summaries, and propose sequence labeling based systems for negation and scope detection. Our systems rely on features from bag of characters, bag of words, character embedding and word embedding. For scopes, we introduce an additional feature to handle nested scopes with multiple negations. ResultsThe two annotators reached an agreement of 0.79 measured by Kappa in manual annotation. In cue detection, our systems are able to achieve a performance as high as 99.0% measured by F score, which significantly outperform its rule-based counterpart (79% F). The best system uses word embedding as features, which yields precision of 99.0% and recall of 99.1%. In scope detection, our system is able to achieve a performance of 94.6% measured by F score. ConclusionsOur study provides a state-of-the-art negation-detecting tool for Chinese clinical free-text notes; Experimental results demonstrate that word embedding is effective in identifying negations, and that nested scopes can be identified effectively by our method.

An automatic key medical information generating model

Present-day society shows keen interest in the field of medical treatment, and the diagnostic mode is now developing toward doctor–patient shared decision-making. Therefore, a patient׳s source of medical information is quite important, with that source needing to be reliable, accurate, and easily accessible. Ensuring that informational sources meet these requirements becomes a challenge with the development of the informational network, which causes the amount of material available online to steadily increase and the general public to become more aware of health- and medical-treatment-related information. Therefore, focusing on the medical information seeker, this paper will discuss two user identities: patients and healthcare professionals. For patients, online medical articles are a major source of medical information; patients with concerns about diseases often search for their symptoms on the Internet and look for related medical information. However, online medical articles are usually long, so patients sometimes self-diagnose their disease or determine the severity of their condition based on only part of an article or on limited, incomplete, or even inaccurate information in several articles related to the symptoms searched out. Consequently, patients may misdiagnose their condition or underestimate the severity or seriousness of the condition and delay treatment. In addition, present medical technology advances rapidly, so physicians and other healthcare professionals must obtain the latest medical information from the Internet. However, searching for and reading professional in-depth medical articles to find required, critical information online is time-consuming, creating a time-management challenge.To address these aforementioned problems, this paper develops an Automatic Key Medical Information Generating model, uses medical articles as the basis of analysis, and develops and designs a medical article key-information-generating methodology applicable to medical article retrieval and reading. The word segmentation is implemented for the articles according to the Chinese Knowledge and Information Processing (CKIP) of Academia Sinica, and the medical articles are then distributed to various clusters by the clustering technology of this model, so that the medical information seeker can conduct a rapid search for the required medical article information. When the medical information seeker finds the target medical article, the article׳s key statements are screened out by the keywords rule base created in this paper, and the key statement scores are calculated. The medical article key information is sequenced according to the key statements so as to generate the medical article key information table. In addition, a web-based key-medical-information-generating system will be built based on the proposed model, and the effectiveness and feasibility of the model and technology will be evaluated using a real-world case.In summary, this paper presents a model to analyze the keywords and key statements of medical articles to generate a medical article key information table. This model can help the medical information seeker look for the required health information rapidly and accurately on the Internet, shortening the time for screening medical information and increasing the probability of obtaining the required information.