-
Chinese Text Sentiment Analysis Based on BERT-BiGRU Fusion Gated Attention
Huang Shufen,
Liu Changhui,
Zhang Yinglin
Issue:
Volume 6, Issue 2, June 2023
Pages:
50-56
Received:
22 March 2023
Accepted:
18 April 2023
Published:
24 April 2023
Abstract: To address the problem that Word2vec static encoding cannot give accurate word vectors about contextual semantics and cannot solve the problem of multiple meanings of words, we propose to use the BERT pre-training model as a word embedding layer to obtain word vectors dynamically; we introduce the gating idea to improve on the traditional attention mechanism and propose BERT-BiGRU-GANet model. The model firstly uses the BERT pre-training model as the word vector layer to vectorize the input text by dynamic encoding; secondly, uses the bi-directional gated recursive unit model (BiGRU) to capture the dependencies between long discourse and further analyze the contextual semantics; finally, before output classification, adds the attention mechanism of fusion gating to ignore the features with little relevance and highlight the key features with weight ratio features. We conducted several comparison experiments on the Jingdong public product review dataset, and the model achieved an F1 value of 93.06%, which is 3.41%, 2.55%, and 1.12% more accurate than the BiLSTM, BiLSTM-Att, and BERT-BiGRU models, respectively. It indicates that the use of the BERT-BiGRU-GANet model has some improvement on Chinese text sentiment analysis, which is helpful in the analysis of goods and service reviews, for consumers to select goods, and for merchants to improve their goods or service reviews.
Abstract: To address the problem that Word2vec static encoding cannot give accurate word vectors about contextual semantics and cannot solve the problem of multiple meanings of words, we propose to use the BERT pre-training model as a word embedding layer to obtain word vectors dynamically; we introduce the gating idea to improve on the traditional attention...
Show More
-
The Application of Multimedia Technology in Business English Teaching in Higher Vocational Schools
Liu Zhijun,
Badarch Tuyatsetseg
Issue:
Volume 6, Issue 2, June 2023
Pages:
57-66
Received:
6 April 2023
Accepted:
5 May 2023
Published:
24 May 2023
Abstract: This paper presents development the multimedia courseware suitable for the teaching of business English in higher vocational colleges. The multimedia courseware helps to enhance the combination of information technology, science, art, and modern methods in classroom teaching. The paper analyzes the design of multimedia technology to achieve interactive teaching based on the principles of multimedia courseware and teaching characteristics of business English. The whole design process of courseware is centered on how to make, organize and display the interface on the courseware. All teaching links need to be completed in each interface jump. The research results show the interactivity of multimedia courseware that can improve students’ ability to improve self-study skills and interaction between the students and instructors. The research focuses on the overall structure, interactive design, and presentation mode of each part of the courseware in detail. Finally, the courseware is comprehensively evaluated by teaching applications and questionnaire surveys. As for the courseware itself, it mainly focuses on the basics of business English, with a few multimedia courses on visualization, listening, and training. Through the research on the use and effect of the multimedia courseware of business English in the classroom, the experimental data is obtained, and results are analyzed to test the effect of the multimedia courseware in the interactive teaching of business English in higher vocational colleges.
Abstract: This paper presents development the multimedia courseware suitable for the teaching of business English in higher vocational colleges. The multimedia courseware helps to enhance the combination of information technology, science, art, and modern methods in classroom teaching. The paper analyzes the design of multimedia technology to achieve interac...
Show More
-
Chinese NER with Softlexion and Residual Gated CNNs
Zhang Yinglin,
Liu Changhui,
Huang Shufen
Issue:
Volume 6, Issue 2, June 2023
Pages:
67-73
Received:
20 April 2023
Accepted:
18 May 2023
Published:
29 May 2023
Abstract: The increment of accuracy and speed on Named Entity Recognition (NER), a key task in natural language processing, can further enhance downstream tasks. The method of residual gated convolution and attention mechanism is proposed to address the problem of insufficient recognition of nested entities and ambiguous entities by convolutional layers in the absence of context. It emphasizes local continuous features fusion to global ones to better obtain contextual semantic information in the stacked convolutional layer. Moreover, the optimized embedding layer with fusing character and lexical information by introducing a dictionary combines with a pre-trained BERT model containing a priori semantic effects, and the decoding layer in an entity-level method to alleviate the problem of nested entities and ambiguous entities in long-sequence text. In order to reduce abundant parameters of Bert model, during the training process, only the residual gated convolutional layer is iterated after fixing Bert layer parameters. After experiments on MSRA corpus, the result of entity recognition task in BERT-softlexion-RGCNN-GP model outperforms other models, with an F1 value of 94.96%, and the training speed is also better than that of the bidirectional LSTM model. Our model not only maintains a more efficient training speed but also recognizes Chinese entities more precisely, which is of practical value for fields required accuracy and speed.
Abstract: The increment of accuracy and speed on Named Entity Recognition (NER), a key task in natural language processing, can further enhance downstream tasks. The method of residual gated convolution and attention mechanism is proposed to address the problem of insufficient recognition of nested entities and ambiguous entities by convolutional layers in t...
Show More
-
Artificial Intelligence and the Future of Web 3.0: Opportunities and Challenges Ahead
Issue:
Volume 6, Issue 2, June 2023
Pages:
74-79
Received:
7 May 2023
Accepted:
26 May 2023
Published:
15 June 2023
Abstract: Artificial Intelligence (AI) has emerged as a key driver of innovation in the digital era, offering new possibilities for the development of Web 3.0. Web 3.0 represents the next evolution of the internet, characterized by decentralized systems, peer-to-peer networks, and advanced technologies such as blockchain and smart contracts. In this paper, we provide an overview of the role of AI in the development of Web 3.0, its opportunities, and challenges. AI can be used to process and analyze large amounts of data more effectively, enabling more intelligent decision-making and insights. We review the key concepts and technologies of Web 3.0, including the Semantic Web, and ontologies, and highlight the potential of AI to transform various industries, including healthcare, finance, and education. We also analyze the challenges of AI in Web 3.0, including data privacy, bias, trust, and ethics, and discuss the potential implications of AI in Web 3.0 for society as a whole. Finally, we outline the future directions and implications of AI in Web 3.0, and recommend areas for future research. Our paper contributes to a better understanding of the potential impact of AI on the development of the web and its implications for society as a whole.
Abstract: Artificial Intelligence (AI) has emerged as a key driver of innovation in the digital era, offering new possibilities for the development of Web 3.0. Web 3.0 represents the next evolution of the internet, characterized by decentralized systems, peer-to-peer networks, and advanced technologies such as blockchain and smart contracts. In this paper, w...
Show More
-
Expert System for Control and Maintenance of Steam Package Boiler Drum and Feed Water Using Rule-Based Fuzzy Logic Techniques
Boye Aziboledia Frederick,
Daniel Matthias,
Onate Egerton Taylor
Issue:
Volume 6, Issue 2, June 2023
Pages:
80-95
Received:
18 May 2022
Accepted:
5 October 2022
Published:
27 June 2023
Abstract: Expert system as a branch in artificial intelligence have impact greatly in many fields of discipline experimentally with various applications. This paper presents research work for expert system for steam package boiler control and maintenance using rule-base fuzzy logic technologies. The system handles cause of boiler errors in terms of control and maintaining the level in boiler drum and feed water variables. The methodology used was quantitative and qualitative as the system validates the consistency, correctness, and its precision on the test value cases, with twenty-one (21) boiler domain practitioners on dynamic simulation. The boiler variables with less or higher test value worst-cases validates the system, indicating red on the boiler’s panel, while on test value best-cases, validates the system, indicating green on the boiler’s panel as end users entered the right values. The steam package boiler system prevents damaged and controls its alkalinity, scaling, chemical corrosion, forming, correct pH values and then conductivity which deals with the feed boiler water and monitored the level in the boiler drum using the industry process parameters, pressure, temperature, level, and flow. The system mean (µ) error on auto run mode was computed as 1.5. The system can be deployed in chemical plants, oil, and gas industry etc. where steam package boilers are needed for steam generation and to reduced need for draughting.
Abstract: Expert system as a branch in artificial intelligence have impact greatly in many fields of discipline experimentally with various applications. This paper presents research work for expert system for steam package boiler control and maintenance using rule-base fuzzy logic technologies. The system handles cause of boiler errors in terms of control a...
Show More
