检索结果-内蒙古大学图书馆

15th IEEE International Conference on Knowledge Graph, ICKG 2024

作者： Jiang, Boran Wang, Yuqi Luo, Yi He, Dawei Cheng, Peng Gao, Liangcai Peking University The Institute of Computer Science and Technology Beijing China Organization State Key Laboratory of Media Convergence Production Technology and Systems Beijing China

ISBN: (纸本)9798331508821

Large language models (LLMs), such as GPT3.5, GPT4 and LLAMA2 perform surprisingly well and outperform human experts on many tasks. However, in many domain-specific evaluations, these LLMs often suffer from hallucination problems due to insufficient training of relevant corpus. Furthermore, fine-tuning large models may face problems such as the LLMs are not open source or the construction of high-quality domain instruction is difficult. Therefore, structured knowledge databases such as knowledge graph can better provide domain background knowledge for LLMs and make full use of the reasoning and analysis capabilities of LLMs. In some previous works, LLM was called multiple times to determine whether the current triplet was suitable for inclusion in the subgraph when retrieving subgraphs through a question. Especially for the question that require a multi-hop reasoning path, frequent calls to LLM will consume a lot of computing power. Moreover, when choosing the reasoning path, LLM will be called once for each step, and if one of the steps is selected incorrectly, it will lead to the accumulation of errors in the following steps. In this paper, we proposed an method of reasoning on efficient knowledge paths (RoK). This method can integrated and optimized the pipeline for selecting reasoning paths from KG based on LLM, which can reduce the dependency on LLM. In addition, we propose a simple and effective subgraph retrieval method based on chain of thought (CoT) and page rank which can returns the paths most likely to contain the answer. We conduct experiments on three datasets: GenMedGPT-5k [14], WebQuestions [2], and CMCQA [21]. Finally, RoK can demonstrate that using fewer LLM calls can achieve the same results as previous SOTAs models. © 2024 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Image Matters: A New Dataset and Empirical Study for Multimodal Hyperbole Detection 30

Image Matters: A New Dataset and Empirical Study for Multimo...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Zhang, Huixuan Wan, Xiaojun Wangxuan Institute of Computer Technology Peking University State Key Laboratory of Media Convergence Production Technology and Systems China

ISBN: (纸本)9782493814104

Hyperbole, or exaggeration, is a common linguistic phenomenon. The detection of hyperbole is an important part of understanding human expression. There have been several studies on hyperbole detection, but most of which focus on text modality only. However, with the development of social media, people can create hyperbolic expressions with various modalities, including text, images, videos, etc. In this paper, we focus on multimodal hyperbole detection. We create a multimodal detection dataset from Weibo (a Chinese social media) and carry out some studies on it. We treat the text and image from a piece of weibo as two modalities and explore the role of text and image for hyperbole detection. Different pre-trained multimodal encoders are also evaluated on this downstream task to show their performance. Besides, since this dataset is constructed from five different keywords, we also evaluate the cross-domain performance of different models. These studies can serve as a benchmark and point out the direction of further study on multimodal hyperbole detection. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Is Summary Useful or Not? An Extrinsic Human Evaluation of Text Summaries on Downstream Tasks 30

Is Summary Useful or Not? An Extrinsic Human Evaluation of T...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Pu, Xiao Gao, Mingqi Wan, Xiaojun Wangxuan Institute of Computer Technology Peking University State Key Laboratory of Media Convergence Production Technology and Systems China

ISBN: (纸本)9782493814104

Research on automated text summarization typically uses human and automatic evaluation methods. While most recent studies focus on intrinsic evaluation, which assesses the general quality of summaries, e.g. coherence and informativeness, we concentrate on task-based extrinsic evaluation to determine the usefulness of summaries. We incorporate three downstream tasks, namely question answering, text classification, and text similarity assessment, and measure the usefulness of summaries for these tasks by several metrics. Our findings reveal that summaries are generally useful in tasks that require a comprehensive grasp of the text but are less useful in tasks requiring a more specific understanding of the text. We also analyze the usefulness and inherent properties of summaries from different models, and find that fine-tuned models consistently produce more useful summaries across all three tasks. In contrast, zero-shot models tend to lean towards text classification and similarity assessment, providing more general and less detailed summaries. Additionally, we assess the correlation between 14 intrinsic automatic metrics and human judgments. Intrinsic metrics perform well in evaluating summaries for question answering but are less effective in the other two tasks. This highlights the limitations of relying solely on intrinsic metrics for assessing summary performance and usefulness. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

ERNCLS: A Cross-Lingual Text Summarization Model Integrating Entity Relation Extraction Task 3

ERNCLS: A Cross-Lingual Text Summarization Model Integrating...

引用

3rd IEEE International Conference on Information technology, Big Data and Artificial Intelligence, ICIBA 2023

作者： Liu, Zhaohong Cao, Juan Yu, Jia Chen, Guowei He, Qiang Communication University of China State Key Laboratory of Media Convergence and Communication Beijing China State Key Laboratory of Media Convergence Production Technology and Systems Beijing China

ISBN: (纸本)9781665490788

The current research on generative cross-lingual summarization models mainly adopts the framework of seq2seq, where entity relation errors are inevitable. How to reduce the occurrence of errors and improve the accuracy of summary generation needs to be addressed urgently. In this regard, we try to add the task of extracting entity relations as an auxiliary task in the Chinese-to-English cross-lingual text summarization model to reduce the entity relation errors in the summaries, and propose two fusion strategies for merging the auxiliary task. In addition, we also adjust the dataset for this task. The experiment proves that it is effective to reduce errors as well as improve the performance of cross-lingual text summarization model by merging the auxiliary task of extracting entity relations in the way of splicing summaries and entity relation triples as real labels of training sets. © 2023 IEEE.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Error-Robust Retrieval for Chinese Spelling Check 30

Error-Robust Retrieval for Chinese Spelling Check

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Yin, Xunjian Hu, Xinyu Jiang, Jin Wan, Xiaojun Wangxuan Institute of Computer Technology Peking University Center for Data Science State Key Laboratory of Media Convergence Production Technology and Systems China

ISBN: (纸本)9782493814104

Chinese Spelling Check (CSC) aims to detect and correct error tokens in Chinese contexts, which has a wide range of applications. However, it is confronted with the challenges of insufficient annotated data and the issue that previous methods may actually not fully leverage the existing datasets. In this paper, we introduce our plug-and-play retrieval method with error-robust information for Chinese Spelling Check (RERIC), which can be directly applied to existing CSC models. The datastore for retrieval is built completely based on the training data, with elaborate designs according to the characteristics of CSC. Specifically, we employ multimodal representations that fuse phonetic, morphologic, and contextual information in the calculation of query and key during retrieval to enhance robustness against potential errors. Furthermore, in order to better judge the retrieved candidates, the n-gram surrounding the token to be checked is regarded as the value and utilized for specific reranking. The experiment results on the SIGHAN benchmarks demonstrate that our proposed method achieves substantial improvements over existing work. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Utilizing spatio-temporal feature fusion in videos for detecting the fluidity of coal water slurry

引用

International Journal of Mining Science and technology 2024年第11期34卷 1587-1597页

作者： Meijie Sun Ziqi Lv Zhiqiang Xu Haimei Lv Yanan Tu Weidong Wang School of Chemical&Environmental Engineering China University of Mining&Technology(Beijing)Beijing 100083China Inner Mongolia Research Institute China University of Mining&Technology(Beijing)Ordos 017001China State Key Laboratory of Media Convergence Production Technology and Systems Beijing 100803China

The fluidity of coal-water slurry(CWS)is crucial for various industrial applications such as long-distance transportation,gasification,and ***,there is currently a lack of rapid and accurate detection methods for assessing CWS *** paper proposed a method for analyzing the fluidity using videos of CWS dripping *** integrating the temporal and spatial features of each frame in the video,a multi-cascade classifier for CWS fluidity is *** classifier distinguishes between four levels(A,B,C,and D)based on the quality of *** preliminary classification of A and D is achieved through feature engineering and the XGBoost ***,convolutional neural networks(CNN)and long short-term memory(LSTM)are utilized to further differentiate between the B and C categories which are prone to ***,through detailed comparative experiments,the paper demonstrates the step-by-step design process of the proposed method and the superiority of the final *** proposed method achieves an accuracy rate of over 90%in determining the fluidity of CWS,serving as a technical reference for future industrial applications.

关键词： Coal water slurry Spatio-temporal feature CNN-LSTM Video classification Machine vision

来源：评论

学校读者我要写书评

暂无评论

A Novel Neural Network-based Data Observation Method for Zeeman Detection 41

A Novel Neural Network-based Data Observation Method for Zee...

引用

第41届中国控制会议

作者： Shuhan Li Yonxing Wang Zizhao Chen UWC Changshu China State Key Laboratory of Media Convergence Production Technology and Systems Xinhua News Agency

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Zeeman effect characterizes the phenomenon that a spectral line is split into several components in the presence of a static magnetic *** is very important in applications,such as magnetic resonance imaging,nuclear magnetic resonance spectroscopy and atomic absorption *** measurement was used in Di Li's recent Nature paper to reveal a coherent magnetic field from the atomic cold neutral medium to the molecular *** paper proposes a novel data observation based on neural network for Zeeman detection,which provides a different way to learn data feature *** results show that our method can fit the data in Li's paper well.

关键词： Data Observation Neural Network Zeeman Detection

来源：评论

学校读者我要写书评

暂无评论

PPTC-R benchmark: Towards Evaluating the Robustness of Large Language Models for PowerPoint Task Completion

PPTC-R benchmark: Towards Evaluating the Robustness of Large...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Zhang, Zekai Guo, Yiduo Liang, Yaobo Zhao, Dongyan Duan, Nan Peking University China Microsoft Research Asia China State Key Laboratory of Media Convergence Production Technology and Systems China Artificial Intelligence Institute of Peking University China

ISBN: (纸本)9798891761681

The growing dependence on Large Language Models (LLMs) for completing user instructions necessitates a comprehensive understanding of their robustness in real-world situations. To address this need, we introduce the PowerPoint Task Completion-Robustness (PPTC-R) benchmark, designed to evaluate LLMs' robustness to user task instructions and different software versions (PowerPoint versions). Specifically, we create adversarial user instructions by manipulating instructions at the sentence, semantic, and language levels. To assess robustness across software versions, we vary the number of available APIs to simulate both the latest and earlier version environments. We benchmark 3 closed-source and 4 open-source LLMs against these robustness settings to evaluate how variations affect their API calls for task completion. Our findings reveal that GPT-4 demonstrates the highest performance and strong robustness, especially in version updates and multilingual settings. However, all LLMs show a significant decline in robustness when faced with multiple simultaneous challenges (e.g., multi-turn interactions), resulting in notable performance drops. We further analyze the robustness behavior and error patterns of LLMs in our benchmark, providing valuable insights for researchers to understand LLM robustness in task completion and to develop more resilient LLMs and agents. The code and data are available at https://***/ZekaiGalaxy/PPTCR. © 2024 Association for Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

UHGEval: Benchmarking the Hallucination of Chinese Large Language Models via Unconstrained Generation 62

UHGEval: Benchmarking the Hallucination of Chinese Large Lan...

引用

62nd Annual Meeting of the Association for Computational Linguistics, ACL 2024

作者： Liang, Xun Song, Shichao Niu, Simin Li, Zhiyu Xiong, Feiyu Tang, Bo Wang, Yezhaohui He, Dawei Cheng, Peng Wang, Zhonghao Deng, Haiying School of Information Renmin University of China Beijing China Institute for Advanced Algorithms Research Shanghai China State Key Laboratory of Media Convergence Production Technology and Systems Beijing China

ISBN: (纸本)9798891760943

Large language models (LLMs) produce hallucinated text, compromising their practical utility in professional contexts. To assess the reliability of LLMs, numerous initiatives have developed benchmark evaluations for hallucination phenomena. However, they often employ constrained generation techniques to produce the evaluation dataset due to cost and time limitations. For instance, this may involve employing directed hallucination induction or deliberately modifying authentic text to generate hallucinations. These are not congruent with the unrestricted text generation demanded by real-world applications. Furthermore, a well-established Chinese-language dataset dedicated to the evaluation of hallucinations is presently lacking. Consequently, we have developed an Unconstrained Hallucination Generation Evaluation (UHGEval) benchmark, containing hallucinations generated by LLMs with minimal restrictions. Concurrently, we have established a comprehensive benchmark evaluation framework to aid subsequent researchers in undertaking scalable and reproducible experiments. We have also evaluated prominent Chinese LLMs and the GPT series models to derive insights regarding hallucination. © 2024 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

Depth First:Optimal Path Discovery Between Designated Nodes in Random Ring-Based Graphs

引用

China Communications 2024年第9期21卷 225-241页

作者： Li Qi Xu Jiasheng Zhang Haonan Kang Huquan Fu Luoyi Long Fei Wang Xinbing Department of Electronic Engineering Shanghai Jiao Tong UniversityShanghai 200240China Department of Computer Science and Engineering Shanghai Jiao Tong UniversityShanghai 200240China State Key Laboratory of Media Convergence Production Technology and Systems Xinhua News AgencyBeijing 100077China

This paper focuses on optimally determining the existence of connected paths between some given nodes in random ring-based *** as a fundamental underlying structure in network modeling,ring topology appears as commonplace in many realistic *** this,we consider graphs composed of rings,with some possible connected paths between *** prior knowledge of the exact node permutations on rings,the existence of each edge can be unraveled through edge testing at a unit cost in one *** problem examined is that of determining whether the given nodes are connected by a path or separated by a cut,with the minimum expected costs *** the problem into different cases based on different topologies of the ring-based networks,we propose the corresponding policies that aim to quickly seek the paths between nodes.A common feature shared by all those policies is that we stick to going in the same direction during edge searching,with edge testing in each step only involving the test between the source and the node that has been tested *** simple searching rule,interestingly,can be interpreted as a delightful property stemming from the neat structure of ring-based networks,which makes the searching process not rely on any sophisticated *** prove the optimality of the proposed policies by calculating the expected cost incurred and making a comparison with the other class of *** effectiveness of the proposed policies is also verified through extensive simulations,from which we even disclose three extra intriguing findings:i)in a onering network,the cost will grow drastically with the number of designated nodes when the number is small and will grow slightly when that number is large;ii)in ring-based network,Depth First is optimal in detecting the connectivity between designated nodes;iii)the problem of multi-ring networks shares large similarity with that of two-ring networks,and a larger number of ties between ri

关键词： connectivity analysis cost minimization path discover ring-based graph

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：