检索结果-内蒙古大学图书馆

2023 international conference on Computer engineering and Distance Learning, CEDL 2023

作者： Zhou, Jing Wuhan Business University School of Information Engineering Hubei Province Wuhan City China

ISBN: (纸本)9798350329032

With the development of deep learning and the knowledge graph, artificial intelligence has had a significant influence on the area of education as a result of the rapid growth of this age, which has profoundly altered human productivity and daily life. The university is undergoing a digital transformation. The essence of the knowledge graph is the knowledge base of the semantic network. Using natural language processing (NLP) technology, the university can construct a knowledge graph. Integrating knowledge graphs and deep learning has become one of the most important aspects of further improving the effect of deep learning. The solution to knowledge graph processing data is 'algorithm, totalization, and implementation'. The key technologies of constructing knowledge graphs in multi-dimensional data mainly focus on knowledge ontology definition, knowledge representation, knowledge modeling, knowledge extraction, knowledge fusion, knowledge processing, knowledge computing, and other technologies. The research in this paper shows that the RDF model and algorithm of the knowledge graph have application prospects in multi-dimensional data. © 2023 IEEE.

关键词： knowledge graph

来源：评论

学校读者我要写书评

暂无评论

FinMoE: A MoE-based Large Chinese Financial language Model 9

FinMoE: A MoE-based Large Chinese Financial Language Model

引用

Joint Workshop of the 9th Financial Technology and natural language processing, FinNLP 2025, the 6th Financial Narrative processing, FNP 2025, and the 1st Workshop on Large language Models for Finance and Legal, LLMFinLegal 2025, co-located with the 31st international conference on Computational Linguistics, COLING 2025

作者： Zhang, Xuanyu Yang, Qing Du Xiaoman Financial Beijing China

ISBN: (纸本)9798891762091

Large-scale language models have demonstrated remarkable success, achieving strong performance across a variety of general tasks. However, when applied to domain-specific fields, such as finance, these models face challenges due to the need for both specialized knowledge and robust general capabilities. In this paper, we introduce FinMoE, a MOE-based large-scale Chinese financial language model that bridges the gap between general language models and domain-specific requirements. FinMoE employs a dense MoE architecture, where all expert networks are simultaneously activated and dynamically combined to effectively integrate general linguistic understanding with domain-specific financial expertise. Experimental results demonstrate that FinMoE achieves state-of-the-art performance on both general-purpose and financial benchmarks at a comparable scale, validating its ability to balance domain specialization with general knowledge and reasoning. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Attention Distillation for Accuracy Improvement of Vision Transformer 12

Attention Distillation for Accuracy Improvement of Vision Tr...

引用

12th IEEE international conference on Identification, Information and knowledge in the Internet of Things, IIKI 2024

作者： Tanaka, Taiga Ishibashi, Ryuto Meng, Lin Ritsumeikan University Graduate School of Science and Engineering 1-1-1 Noji-higashi Shiga Kusatsu525-8577 Japan Ritsumeikan University College of Science and Engineering 1-1-1 Noji-higashi Shiga Kusatsu525-8577 Japan

ISBN: (纸本)9798331510633

In recent years, rapid advancements in technology have propelled progress in the fields of image recognition and natural language processing, resulting in the development of numerous applications and services. In particular, the advancement of deep learning has greatly contributed to improving the accuracy of these fields, and the use of AI is becoming more widespread in everyday life [1]. Among them, Vision Transformers (ViT) has emerged as a robust architecture in image recognition. ViT requires a large dataset for training to improve accuracy. To solve this problem, DeiT using knowledge distillation has been proposed. However, this DeiT does not consider each token's contribution to [CLS] in learning. In this study, a knowledge distillation model training method called ADViT that uses the contribution of each token to Classify token ([CLS]) is proposed. Specifically, the attention map of each token for [CLS] is calculated. In each layer, learning is performed to bring the student model's attention map closer to the teacher model's attention map. Then, the accuracy is evaluated, and experimental results show the effectiveness of the proposed method, with accuracy rates of ADViT-Tiny(L1): 98.35%, ADViT-Tiny(L2): 98.06%, ADViT-Small(L1):99.00%, and ADViT-Small(L2): 98.75%, which are higher than those of DeiT, DeiT-Tiny: 96.39%, DeiT-Small: 96.83%. Future work includes managing the number of heads and reducing the computation for more optimization. © 2024 IEEE.

关键词： natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

language Models over Large-Scale knowledge Base: on Capacity, Flexibility and Reasoning for New Facts 31

Language Models over Large-Scale Knowledge Base: on Capacity...

引用

31st international conference on Computational Linguistics, COLING 2025

作者： He, Qiyuan Wang, Yizhong Yu, Jianfei Wang, Wenya College of Computing and Data Science Nanyang Technological University Singapore Paul G. Allen School of Computer Science & Engineering University of Washington United States School of Computer Science and Engineering Nanjing University of Science and Technology China

ISBN: (纸本)9798891761964

Advancements in language models (LMs) have sparked interest in exploring their potential as knowledge bases (KBs) due to their high capability for storing huge amounts of factual knowledge and semantic understanding. However, existing studies face challenges in quantifying the extent of large-scale knowledge packed into LMs and lack systematic studies on LMs' structured reasoning capabilities over the infused knowledge. Addressing these gaps, our research investigates whether LMs can effectively act as large-scale KBs after training over an expansive set of world knowledge triplets via addressing the following three crucial questions: (1) How do LMs of different sizes perform at storing world knowledge of different frequencies in a large-scale KB? (2) How flexible are these LMs in recalling the stored knowledge when prompted with natural language queries? (3) After training on the abundant world knowledge, can LMs additionally gain the ability to reason over such information to infer new facts? Our findings indicate that while medium-scaled LMs hold promise as world knowledge bases capable of storing and responding with flexibility, enhancements in their reasoning capabilities are necessary to fully realize their potential. © 2025 Association for Computational Linguistics.

关键词： Structured Query language

来源：评论

学校读者我要写书评

暂无评论

Role of natural language processing and Machine Learning on (MTS)-Machine Translation System for Indian languages: A Review 15

Role of Natural Language Processing and Machine Learning on ...

引用

15th international conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Megha, V. Pooja, M.R. Vidyavardhaka College of Engineering Mysuru India

ISBN: (纸本)9798331300579

The conversion process of one specific language to another either in a completely automatic manner or with considerable amount of human intervention by preserving the original meaning of the input source text is known as (MTS) Machine Translation System. The expeditious availability of data and the need for increased processing speed of information has led the way towards natural language processing, Machine Learning, Speech processing, Image processing etc. When it comes to the Indian regional languages the research in this domain is very minimal as an outcome there is limited resources. In this paper, the researcher will be able to know the general workflow of how the translation process of source to destination language will occur and the various approaches and the methods for processing Indian languages proposed by scientists which are verified and validated, the challenges a researcher would face while developing one such translation tool followed by the summary of the entire review. © Grenze Scientific Society, 2024.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Simulation of Structured natural language Algorithm on Cloud Computing 3

Simulation of Structured Natural Language Algorithm on Cloud...

引用

3rd IEEE international conference on Electrical engineering, Big Data and Algorithms, EEBDA 2024

作者： Fang, Quanrong Tang, Keyin Investment Co. Ltd. Beijing China

ISBN: (纸本)9798350380989

From the sentiment analysis of social media to the monitoring of public opinion in the financial field, the application of natural language analysis continues to expand, and people's demand for natural language processing technology is also increasing. However, traditional natural language analysis algorithms face performance bottlenecks and energy consumption. Therefore, this paper proposes a structured natural language analysis algorithm based on cloud computing. Through simulation experiments, the performance and energy consumption of the algorithm are tested and evaluated. After a comprehensive experimental scheme design, the experimental group is compared with the control group by selecting the appropriate data set and establishing appropriate evaluation indicators, while configuring the experimental environment. The experimental results show that the lowest energy consumption of the algorithm in this paper is 2.41%, and the structured natural language analysis algorithm based on cloud computing has obvious advantages over traditional methods. The proportion of energy consumption in the experimental group is lower than that of the control group, indicating that the algorithm of the experimental group is better in terms of energy utilization efficiency. The performance degradation of the experimental group is lower when processing large-scale data, indicating that the experimental group algorithm has better extensibility and efficiency. These results provide strong support for the application of structured natural language analysis algorithms based on cloud computing, which helps to improve system efficiency and sustainability. © 2024 IEEE.

关键词： algorithm simulation cloud computing natural language structured analysis

来源：评论

学校读者我要写书评

暂无评论

Decoding News Bias: Multi Bias Detection in News Articles 24

Decoding News Bias: Multi Bias Detection in News Articles

引用

8th international conference on natural language processing and Information Retrieval, NLPIR 2024

作者： Shah, Bhushan Santosh Shah, Deven Santosh Attar, Vahida Computer Engineering College of Engineering Pune Technological University Pune India Computer Science Stony Brook University Stony Brook United States

ISBN: (纸本)9798400717383

News Articles provide crucial information about various events happening in the society but they unfortunately come with different kind of biases. These biases can significantly distort public opinion and trust in the media, making it essential to develop techniques to detect and address them. Previous works have majorly worked towards identifying biases in particular domains e.g., Political, gender biases. However, more comprehensive studies are needed to detect biases across diverse domains. Large language models (LLMs) offer a powerful way to analyze and understand natural language, making them ideal for constructing datasets and detecting these biases. In this work, we have explored various biases present in the news articles, built a dataset using LLMs and present results obtained using multiple detection techniques. Our approach highlights the importance of broad-spectrum bias detection and offers new insights for improving the integrity of news articles. © 2024 Copyright held by the owner/author(s).

关键词： Multi Bias Detection

来源：评论

学校读者我要写书评

暂无评论

Converse Attention knowledge Transfer for Low-Resource Named Entity Recognition

引用

international Journal of Crowd Science 2024年第3期8卷 140-148页

作者： Lyu, Shengfei Sun, Linghao Yi, Huixiong Liu, Yong Chen, Huanhuan Miao, Chunyan School of Computer Science and Technology University of Science and Technology of China Hefei230027 China School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore

In recent years, great success has been achieved in many tasks of natural language processing (NLP), e.g., named entity recognition (NER), especially in the high-resource language, i.e., English, thanks in part to the considerable amount of labeled resources. More labeled resources, better word representations. However, most low-resource languages do not have such an abundance of labeled data as high-resource English, leading to poor performance of NER in these low-resource languages due to poor word representations. In the paper, we propose converse attention network (CAN) to augment word representations in low-resource languages from the high-resource language, improving the performance of NER in low-resource languages by transferring knowledge learned in the high-resource language. CAN first translates sentences in low-resource languages into high-resource English using an attention-based translation module. In the process of translation, CAN obtains the attention matrices that align word representations of high-resource language space and low-resource language space. Furthermore, CAN augments word representations learned in low-resource language space with word representations learned in high-resource language space using the attention matrices. Experiments on four low-resource NER datasets show that CAN achieves consistent and significant performance improvements, which indicates the effectiveness of CAN. © The author(s) 2024.

关键词： Labeled data

来源：评论

学校读者我要写书评

暂无评论

Next Word Prediction Using knowledge Graph 2

Next Word Prediction Using Knowledge Graph

引用

2nd international conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Alshiya, S. Usha, K. NSS College of Engineering Dept of Computer Science and Engineering Palakkad India

ISBN: (数字)9798331505745

ISBN: (纸本)9798331505745

Next-word prediction is a fundamental task in natural language processing (NLP) with various applications in intelligent text completion, voice assistants, and human-computer interaction. Most statistical model-based or deep learning-based methods tend to have difficulty modeling both semantic knowledge and long-range contextual dependencies. This work introduces a hybrid next-word prediction model that combines knowledge Graph (KG) embeddings and a Long Short-Term Memory (LSTM) network to improve semantic consciousness and sequential context representation. By tapping into structured relational knowledge in KGs together with the contextual learning abilities of LSTMs, the approach here seeks to enhance predictive precision and semantic consistency. This research fills the gap between structured knowledge representation and neural sequence modeling, paving the way for more context-sensitive and semantically richer next-word prediction models. © 2025 IEEE.

关键词： knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Chinese Text Simplification Based on Large language Models

Chinese Text Simplification Based on Large Language Models

引用

2024 international conference on Computational Linguistics and natural language processing, CLNLP 2024

作者： Huo, Hongying Fu, Zetong Yu, Haochen Yang, Shengguang Tang, Gongbo Beijing Language and Culture University School of Information Science Beijing China

ISBN: (纸本)9798350392098

Chinese is a complex language, creating a demand for text simplification in various contexts. Traditional text simplification models have primarily relied on pre-trained models. With the advancement of large language models (LLMs), researchers have begun leveraging their robust text comprehension and generation capabilities for text simplification tasks. However, these implementations are often simplistic, merely instructing the LLM to simplify text without addressing inherent challenges. One notable issue is the hallucination phenomenon where LLMs introduce inaccuracies, especially in fine-grained knowledge. This paper proposes an approach to interact with LLMs by embedding the text's underlying knowledge through carefully designed prompts. These prompts provide clearer guidance to the LLMs, thereby improving the quality of text simplification. In addition, LLMs may be further improved on specific tasks after instruction fine-tuning. Thus, we constructed a text simplification training dataset with semantic knowledge from Chinese Parataxis graph, and fine-tuned existing large models specifically for the text simplification task. Experimental results demonstrate that fine-tuning LLMs can significantly enhance the quality of text simplification. Finally, we provide the proposed methods as a service via a web interface and a browser extension. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：