检索结果-内蒙古大学图书馆

13th international conference on natural language processing and Chinese Computing

作者： Zeng, Biqing Shi, Hao Li, Yangyu Li, Ruizhe Deng, Huimin South China Normal Univ Sch Software Foshan Peoples R China South China Normal Univ Aberdeen Inst Data Sci & Artificial Intelligence Foshan Peoples R China Univ Aberdeen Dept Comp Sci Aberdeen Scotland Guangdong AIB Polytech Sch Comp Sci Guangzhou Peoples R China

ISBN: (纸本)9789819794331;9789819794348

Large language models(LLMs) have exhibited notable general-purpose task-solving abilities in language understanding and generation, including processing recommendation tasks. The majority of existing research relies on training-free recommendation models that treat LLMs as reasoning engines and directly given the recommended task response. This approach heavily relies on pre-trained knowledge and may lead to excessive costs. As such, we propose a two-stage fine-tuning framework leveraging LLaMA2 and GPT-4 knowledge Enhancement for recommendation. In particular, we use GPT-4 Instruction-Following data to tune the LLM in first-stage instruction tuning process, achieving lower training costs and better inference performance. In the second stage, through a elaborately designed prompt template, we fine-tune LLM from the first stage in a few-shot setting by interactive sequences based on user ratings. To validate the effectiveness of our framework, we compare against state-of-the-art baseline methods on benchmark datasets. The results demonstrate that our framework has promising recommendation capabilities. Our experiments are executed on a single RTX4090 with LLaMA2-7B.

关键词： Large language models knowledge Enhancement Recommendation Instruction Tuning

来源：评论

学校读者我要写书评

暂无评论

Understanding Collaborative Learning Processes and Outcomes Through Student Discourse Dynamics 25

Understanding Collaborative Learning Processes and Outcomes ...

引用

15th international conference on Learning Analytics and knowledge

作者： Park, Seehee Nixon, Nia D'Mello, Sidney Shariff, Danielle Choi, Jaeyoon Univ Calif Irvine Sch Educ Irvine CA 92697 USA Univ Calif Irvine Dept Cognit Sci Irvine CA 92697 USA Univ Colorado Inst Cognit Sci Boulder CO 80309 USA

ISBN: (纸本)9798400707018

This study explores the relation between students' discourse dynamics and performance during collaborative problem-solving activities utilizing Linguistic Inquiry Word Count (LIWC). We analyzed linguistic variables from students' communications to explore social and cognitive behavior. Participants include 279 undergraduate students from two U.S. universities engaged in a controlled lab setting using the physics related educational game named Physics Playground. Findings highlight the relationship between social and cognitive linguistic variables and student's physics performance outcome in a virtual collaborative learning context. This study contributes to a deeper understanding of how these discourse dynamics are related to learning outcomes in collaborative learning. It provides insights for optimizing educational strategies in collaborative remote learning environments. We further discuss the potential for conducting computational linguistic modeling on learner discourse and the role of natural language processing in deriving insights on learning behavior to support collaborative learning.

关键词： Learning Analytics Discourse Analytics natural language processing Collaborative Problem Solving Virtual Learning Environment

来源：评论

学校读者我要写书评

暂无评论

Domain Adaptation for Chinese Offensive language Detection 13th

Domain Adaptation for Chinese Offensive Language Detection

引用

13th international conference on natural language processing and Chinese Computing

作者： Ying, Hao Ou, Qiongrong Fan, Chengjun Mei, Lin Zhang, Shuyu Xu, Xu Fudan Univ Sch Informat Sci & Technol Inst Elect Light Sources State Key Lab Photovolta Sci & Technol Shanghai 200433 Peoples R China DTH Serv China Adm Ctr Beijing 100866 Peoples R China Donghai Lab Zhoushan 316021 Peoples R China

ISBN: (纸本)9789819794393;9789819794409

Accurate detection of offensive language is crucial for maintaining harmony on social media platforms. However, the lack of well-annotated datasets makes it challenging to classify semantically Chinese offensive language using deep learning. To this end, we have studied how to transfer rich corpus knowledge from other languages to Chinese, exploring the impact of data from different cultural backgrounds on the detection of offensive language in Chinese under various conditions. We found that when enough Chinese corpus and labeling information are available, domain adaptation can prevent negative transfers caused by cultural differences while utilizing rich corpus knowledge to enhance detection performance. In a zero-shot learning environment, domain adaptation allows the effective transfer of corpus knowledge from specific languages to Chinese language detection tasks based on the model's linguistic background, thereby enhancing the performance of monolingual models in cross-lingual tasks. Our research indicates that domain adaptation plays a positive role in cross-cultural transfer detection.

关键词： Offensive language Detection Transfer Learning Domain Adaptation

来源：评论

学校读者我要写书评

暂无评论

A Model-Based Evaluation Metric for Question Answering Systems

引用

international JOURNAL OF SOFTWARE engineering AND knowledge engineering 2025年第2期35卷 243-262页

作者： Bakir, Dilan Aktas, Mehmet S. Yildiz, Beytullah Yildiz Tech Univ Comp Engn Dept Istanbul Turkiye Atilim Univ Software Engn Dept Ankara Turkiye

The paper addresses the limitations of traditional evaluation metrics for Question Answering (QA) systems that primarily focus on syntax and n-gram similarity. We propose a novel model-based evaluation metric, MQA-metric, and create a human-judgment-based dataset, squad-qametric and marco-qametric, to validate our approach. The research aims to solve several key problems: the objectivity in dataset labeling, the effectiveness of metrics when there is no syntax similarity, the impact of answer length on metric performance, and the influence of real answer quality on metric results. To tackle these challenges, we designed an interface for dataset labeling and conducted extensive experiments with human reviewers. Our analysis shows that the MQA-metric outperforms traditional metrics like BLEU, ROUGE and METEOR. Unlike existing metrics, MQA-metric leverages semantic comprehension through large language models (LLMs), enabling it to capture contextual nuances and synonymous expressions more effectively. This approach sets a standard for evaluating QA systems by prioritizing semantic accuracy over surface-level similarities. The proposed metric correlates better with human judgment, making it a more reliable tool for evaluating QA systems. Our contributions include the development of a robust evaluation workflow, creation of high-quality datasets, and an extensive comparison with existing evaluation methods. The results indicate that our model-based approach provides a significant improvement in assessing the quality of QA systems, which is crucial for their practical application and trustworthiness.

关键词： Question answering generative model evaluation metric natural language processing transformer models large language model

来源：评论

学校读者我要写书评

暂无评论

Multimodal Learning in natural language processing: Fact-Checking, Ethics and Misinformation Detection

Multimodal Learning in Natural Language Processing: Fact-Che...

引用

2025 international conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Joshi, Himanshu Sanjay Taherdoost, Hamed College of Business Westcliff University CA United States College of Technology & Engineering Westcliff University CA United States University Canada West Vancouver Canada Gus Institute Global University Systems London United Kingdom Q Minded Quark Minded Technology Inc. Vancouver Canada

ISBN: (纸本)9798331509828

Multimodal learning (MML) is a subtype of deep learning that improves the capabilities of machine learning models by integrating modalities from multiple data sources such as text, images, audio, and video. This integration of modalities produces a more comprehensive understanding of complex data and nuanced outputs. Applications of this approach in real-time decision-making, information retrieval, and knowledge representation can improve the insights derived from the natural language processing (NLP) system. Moreover, in a time of information overload, there are concerns regarding the credibility of the content. The role of NLP systems is central to processing textual data in MML systems. In this environment, the ethical development of multimodal systems for fact-checking is crucial. This paper addresses an existing gap in use of multimodal learning in the context of fact-checking by investigating issues related to integration of NLP, Question-Answering (QA) systems, and knowledge graphs to combat misinformation. This research presents multimodal data based frameworks based on knowledge graph integration. The exploration of the frameworks enables to enhance the accuracy, reliability, and ethical soundness of fact-checking mechanisms. This study also highlights new directions for overcoming challenges related to modality alignment, computational efficiency, and ethical transparency. © 2025 IEEE.

关键词： knowledge graph

来源：评论

学校读者我要写书评

暂无评论

GraphLLM: A General Framework for Multi-hop Question Answering over knowledge Graphs Using Large language Models 13th

GraphLLM: A General Framework for Multi-hop Question Answeri...

引用

13th international conference on natural language processing and Chinese Computing

作者： Qi, Zijian Li, Nan Huang, Chenxi Wang, Gangliang Liang, Shenglin Lin, Hui Guo, Qinglang Xiamen Univ Sch Informat Xiamen Peoples R China CETC Acad Elect & Informat Technol Grp Co Ltd Beijing Peoples R China Xidian Univ Xian Peoples R China

ISBN: (纸本)9789819794300;9789819794317

The task of multi-hop question answering over knowledge graphs (KGQA) is designed to identify answer entities for a given question through reasoning across multiple edges over KGs. This task presents persistent challenges: as the number of hops increases, both the reasoning complexity and the pool of candidate answers expand, resulting in sub-optimal outcomes. Due to the powerful semantic understanding and logical reasoning capabilities of large language models, we propose a general framework for multi-hop KQGA using large language models (LLMs), named GraphLLM. Specifically, GraphLLM involves employing the semantic understanding and reasoning abilities of LLMs to decompose multi-hop questions through a Divide-And-Conquer approach and construct sub-graphs, transforming complex problems into several simple sub-questions. We obtain the ultimate answer by iteratively using Graph Neural Networks (GNNs) to solve sub-questions. By conducting experiments on benchmarks WebQSP and MetaQA, results indicate that GraphLLM exhibits outstanding performance compared to leading methods. We successfully demonstrate a collaborative example of LLMs and GNNs, offering a novel approach to addressing intricate multi-hop KGQA.

关键词： Large language Model knowledge Graph Multi-hop Question Answering Graph Neural Network

来源：评论

学校读者我要写书评

暂无评论

Computer-Assisted knowledge Points and Question Difficulty Classification Based on BERT

Computer-Assisted Knowledge Points and Question Difficulty C...

引用

2024 international conference on Mechatronics and Intelligent Control, ICMIC 2024

作者： Zhu, Jia Jun Yang, Zichuan Hong, Binjie Song, Jiacheng Wang, Jiwei Chen, Tianhao Yang, Shuilan Lan, Zixun Ma, Fei Department of Information and Computing Science Xi'an Jiaotong-Liverpool University Suzhou China School of Engineering Suzhou Centennial College Suzhou China Department of Applied Mathematics Xi'an Jiaotong-Liverpool University Suzhou China GROW Inc. Suzhou China EasyStack Inc. Nanjing China TAL Education Group Beijing China

ISBN: (数字)9781510686847

ISBN: (纸本)9781510686830

In recent years, with the increasing use of educational technology and online learning platforms, there has been a growing interest in developing intelligent systems that can automatically predict the knowledge points associated with educational questions. This paper presents a novel approach for knowledge point prediction in middle school mathematics questions. The dataset used in this study consists of a large collection of 591,379 middle school mathematics questions. To leverage the power of natural language processing techniques, the questions are preprocessed using a tokenizer and encoded into word embeddings using BERT (Bidirectional Encoder Representations from Transformers). Matrix dot production is then employed to calculate the similarity between each test question and the training set, and the top-n most similar vectors are selected for each test question. A voting mechanism is introduced to eliminate duplicate knowledge points and rank them based on their total scores in descending order, resulting in k candidate solutions. The performance of the proposed approach is evaluated using top-k accuracy as the evaluation metric and a lowest common ancestor (LCA) algorithm is used to calculate accuracy at different levels of the knowledge point tree. The results demonstrate the effectiveness of the proposed approach in predicting knowledge points for middle school mathematics questions and its potential for application in intelligent tutoring systems and educational assessment tools. © 2025 SPIE.

关键词： natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Automatic Short Answer Grading in the LLM Era: Does GPT-4 with Prompt engineering beat Traditional Models? 25

Automatic Short Answer Grading in the LLM Era: Does GPT-4 wi...

引用

15th international conference on Learning Analytics and knowledge

作者： Mello, Rafael Ferreira Junior, Cleon Pereira Rodrigues, Luiz Pereira, Filipe Dwan Cabral, Luciano Costa, Newarney Ramalho, Geber Gasevic, Dragan Monash Univ Melbourne Vic Australia Inst Fed Goiano Ipora Brazil Univ Fed Alagoas Comp Inst Maceio Alagoas Brazil Univ Fed Roraima Boa Vista Parana Brazil CJBG IFPE CESAR Sch NEES UFAL Jaboatao Guararapes Brazil Univ Fed Pernambuco Recife PE Brazil

ISBN: (纸本)9798400707018

Assessing short answers in educational settings is challenging due to the need for scalability and accuracy, which led to the field of Automatic Short Answer Grading (ASAG). Traditional machine learning models, such as ensemble and embeddings, have been widely researched in ASAG, but they often suffer from generalizability issues. Recently, Large language Models (LLMs) emerged as an alternative to optimize ASAG systems. However, previous research has failed to present a comprehensive analysis of LLMs' performance powered by prompt engineering strategies and compare its capabilities to traditional models. This study presents a comparative analysis between traditional machine learning models and GPT-4 in the context of ASAG. We investigated the effectiveness of different models and text representation techniques and explored prompt engineering strategies for LLMs. The results indicate that traditional machine learning models outperform LLMs. However, GPT-4 showed promising capabilities, especially when configured with optimized prompt components, such as few-shot examples and clear instructions. This study contributes to the literature by providing a detailed evaluation of LLM performance compared to traditional machine learning models in a multilingual ASAG context, offering insights for developing more efficient automatic grading systems.

关键词： Automatic short answer grading natural language processing Assessment LLM GPT

来源：评论

学校读者我要写书评

暂无评论

Multi-layer Sequence Labeling-Based Joint Biomedical Event Extraction 13th

Multi-layer Sequence Labeling-Based Joint Biomedical Event E...

引用

13th international conference on natural language processing and Chinese Computing

作者： Chen, Gongchi Wu, Pengchao Gu, Jinghang Qian, Longhua Zhou, Guodong Soochow Univ Sch Comp Sci & Technol Suzhou 215006 Peoples R China Hong Kong Polytech Univ Dept Chinese & Bilingual Studies Hong Kong 999077 Peoples R China

ISBN: (纸本)9789819794331;9789819794348

In recent years, biomedical event extraction has been dominated by complicated pipeline and joint methods, which need to be simplified. In addition, existing work has not effectively utilized trigger word information explicitly. Hence, we propose MLSL, a method based on multi-layer sequence labeling for joint biomedical event extraction. MLSL does not introduce prior knowledge and complex structures. Moreover, it explicitly incorporates the information of candidate trigger words into the sequence labeling to learn the interaction relationships between trigger words and argument roles. Based on this, MLSL can learn well with just a simple workflow. Extensive experimentation demonstrates the superiority of MLSL in terms of extraction performance compared to other state-of-the-art methods.

关键词： Biomedical event extraction Sequence labeling natural language processing

来源：评论

学校读者我要写书评

暂无评论

Deciphering Excellence in Hospitality: A Study on India's Premier Hotels Using natural language processing 4th

Deciphering Excellence in Hospitality: A Study on India's Pr...

引用

4th international conference on Artificial Intelligence and knowledge processing

作者： Menon, Rajeev Padmanabhan Rege, Manjeet Univ St Thomas Dept Software Engn & Data Sci St Paul MN 55105 USA

ISBN: (纸本)9783031734762;9783031734779

Navigating the dynamic hospitality landscape, premier hotels in India encounter a perpetual challenge: comprehending the intricate factors that drive guest satisfaction. While existing research provides broad insights, the nuances of the luxury segment are often overlooked. This study aims to bridge this gap by meticulously analyzing reviews from over a hundred premier hotels in major metro cities in India, focusing on the 5-star category. The research identifies seven key attributes influencing reviewer perceptions and reveals distinct patterns. Food Quality, Hotel Staff, and Service emerge as powerful predictors of both positive and negative sentiments, while Cleanliness and Comfort exhibit unique impacts. Through the application of logistic regression and sentiment analysis, and natural language processing (NLP) techniques such as tokenization, lemmatization, and VADER sentiment analysis on online reviews, this research quantifies the influence of each attribute. The findings contribute to a deeper understanding of guest expectations and provide actionable insights for hotel management to tailor offerings and enhance guest experiences. This study significantly contributes to the ongoing discourse on customer satisfaction in the hospitality sector in India.

关键词： Sentiment Analysis 5-Star-Hotel Attributes Online Reviews Logistic Regression Customer Satisfaction Text Mining Premier Hotels natural language processing

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：