检索结果-内蒙古大学图书馆

Evaluating the Performance to Detecting Topic Shift of Large Language Models: A Study 9

学校读者我要写书评

暂无评论

Evaluating the Performance to Detecting Topic Shift of Large...

9th International Conference on Intelligent Computing and Signal Processing, ICSP 2024

作者： Tian, Pingfang Liu, Deting Department of Computer Science and Technology Wuhan University of Science and Technology Wuhan430065 China Institute of Scientific and Technical Information of China The Key Laboratory of the Rich Media Knowledge Organisation and Service of Digital Publishing Content Beijing100038 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan China Big Data Science and Engineering Research Institute Wuhan University of Science and Technology Wuhan430065 China

ISBN: (纸本)9798350376548

Topic shift detection aims to identify whether there is a change in the current topic of conversation or if a change is needed. The study found previous work did not evaluate the performance of large language models like ChatGPT on the task of topic shift. Therefore, this paper's main task and innovation lie in analyzing ChatGPT's performance on topic shift detection. To provide a more comprehensive evaluation, we conducted topic shift detection tasks on ChatGPT from three aspects: single utterances, adjacent utterances, and contextual levels. Additionally, to gauge the performance of large language models, we conducted experiments on multiple small-scale models and compared the results of the two models. Experimental results on the publicly available English TIAGE dataset showed that small-scale models exhibited lower recall in all three aspects, while ChatGPT performed better in the recall. This suggests that compared to small-scale models, large models are more capable of accurately detecting topic shifts. However, large models also exhibited lower precision, indicating that while ChatGPT can recognize content differences in utterances, its judgment on whether these different contents belong to the same topic is poor. © 2024 IEEE.

关键词： adjacent utterances level ChatGPT contextual level single utterances level topic shift detection

The Master-Slave Encoder Model for Improving Patent Text Summarization: A New Approach to Combining Specifications and Claims

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhou, Shu Wang, Xin Zhou, Zhengda Yi, Haohan Zheng, Xuhui Wang, Hao School of Information Management Nanjing University China Key Laboratory of Data Engineering and Knowledge Services in Jiangsu Provincial Universities Nanjing University China Baidu Inc. Beijing China

In order to solve the problem of insufficient generation quality caused by traditional patent text abstract generation models only originating from patent specifications, the problem of new terminology OOV caused by rapid patent updates, and the problem of information redundancy caused by insufficient consideration of the high professionalism, accuracy, and uniqueness of patent texts, we proposes a patent text abstract generation model (MSEA) based on a master-slave encoder architecture;Firstly, the MSEA model designs a master-slave encoder, which combines the instructions in the patent text with the claims as input, and fully explores the characteristics and details between the two through the master-slave encoder;Then, the model enhances the consideration of new technical terms in the input sequence based on the pointer network, and further enhances the correlation with the input text by re weighing the "remembered" and "for-gotten" parts of the input sequence from the encoder;Finally, an enhanced repetition suppression mechanism for patent text was introduced to ensure accurate and non redundant abstracts generated. On a publicly available patent text dataset, compared to the state-of-the-art model, Improved Multi-Head Attention Mechanism (IMHAM), the MSEA model achieves an improvement of 0.006, 0.005, and 0.005 in Rouge-1, Rouge-2, and Rouge-L scores, respectively. MSEA leverages the characteristics of patent texts to effectively enhance the quality of patent text generation, demonstrating its advancement and effectiveness in the experiments. Copyright © 2024, The Authors. All rights reserved.

关键词： Specifications

Research on Mathematical Modelling and Analysis Mothod of Vehicle-bridge Coupled Vibration

学校读者我要写书评

暂无评论

Research on Mathematical Modelling and Analysis Mothod of Ve...

2022 IEEE Asia-Pacific Conference on Image Processing, Electronics and Computers, IPEC 2022

作者： Xu, Yichao Zhang, Jian Zhang, Yufeng Southeast University School of Civil Engineering Nanjing211189 China Jsti Group Nanjing211000 China State Key Laboratory of Safety and Health for In-Service Long Span Bridge Nanjing210012 China Ctr. of Data Measured by Struct. Health Monitoring System of Long-Span Bridge in Province of Jiangsu Nanjing210012 China

ISBN: (纸本)9781665409025

The existing vehicle-bridge coupled vibration analysis of the vehicle model cannot accurately consider the vehicle dynamic characteristics and the impact of flexible tires on the vehicle-bridge coupled vibration response. This paper analyzes the surface contact on the vehicle-bridge coupled vibration by establishing a new three-dimensional wheel model The contact surface between the wheel and the road surface is simulated as a rectangle, and the vehicle-bridge coupled vibration equation is established through the coordinated displacement conditions and force interaction between the contact surfaces. The vertical acceleration of bridges and car bodies is significantly affected by track irregularities. Improving line conditions can effectively improve the comfort of trains;at the same time, the higher the speed, the greater the root mean square of the random response of bridges and vehicles, which is caused by track irregularities. The greater the dispersion of the vibration response of the coupled system. © 2022 IEEE.

关键词： Big data

Salient Patch Based NAS for Grading of Colorectal Cancer Histology Images 13

学校读者我要写书评

暂无评论

Salient Patch Based NAS for Grading of Colorectal Cancer His...

13th International Multi-Conference on Complexity, Informatics and Cybernetics, IMCIC 2022

作者： Meng, Hang Li, Fei Yang, Zhen Zhu, Qiang Fan, Chaogang Zhan, Shu Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Hefei University of Technology Anhui Province Hefei230009 China The Second Affiliated Hospital of Anhui Medical University Anhui Province Hefei230601 China Tongcheng Teachers College Anhui Province Tongcheng231400 China Department of General Surgery The Affiliated BenQ Hospital of Nanjing Medical University Jiangsu Province Nanjing210021 China

ISBN: (纸本)9781950492619

Digital histopathological tissue images are gold material for cancer diagnosis and grades. Convolutional Neural Networks (CNNs) are state-of-the-art models in many image classification tasks. However, considering the limited computing resources, it is not practical to directly train CNNs on gigapixel resolution histopathological tissue images. Therefore, the entire histopathological image is commonly divided into a grid of patches and then fed each patch to CNNs, but not all patches are necessary for specific tasks. Besides, although CNNs are excellent image classifiers, many pre-trained models are based on natural images. Neural Architecture Search (NAS) can realize automatic search, construction, and training specific problemoriented networks. We present salient patch based NAS for grading colorectal cancer (CRC) histology images with these motivations. The proposed framework first applies the classic classification network to extract significant patches from the whole image, then use the network obtained by NAS to grade the patches, and finally aggregates the patch-level predictions to generate the entire CRC histological image label. Our experiments on microscopic colorectal tissue images demonstrate that the proposed method is sufficient to obtain more accurate classification results compared to its counterparts. We also conducted a comprehensive analysis of the different scenarios of the proposed method. © by the International Institute of Informatics and Systemics.

关键词： Grading

SAMPLING LOVÁSZ LOCAL LEMMA FOR GENERAL CONSTRAINT SATISFACTION SOLUTIONS IN NEAR-LINEAR TIME

学校读者我要写书评

暂无评论

arXiv 2022年

作者： He, Kun Wang, Chunyang Yin, Yitong The Key Lab of Data Engineering and Knowledge Engineering MOE Renmin University of China No. 59 Zhongguancun Street Haidian District Beijing China State Key Laboratory for Novel Software Technology Nanjing University 163 Xianlin Avenue Jiangsu Province Nanjing China

We give a fast algorithm for sampling uniform solutions of general constraint satisfaction problems (CSPs) in a local lemma regime. Suppose that the CSP has n variables with domain size at most q, each constraint contains at most k variables, shares variables with at most Δ constraints, and is violated with probability at most p by a uniform random assignment. The algorithm returns an almost uniform satisfying assignment in expected poly(q,k, Δ) ·(n) time, as long as a local lemma condition is satisfied: k · p · q2 · Δ5 ≤ C0 for a suitably small absolute constant C0. Previously, under similar local lemma conditions, sampling algorithms with running time polynomial in both nand Δ were only known for the almost atomic case, where each constraint is violated by a small number of forbidden local configurations. The key term Δ5 in our local lemma condition also improves the previously best known Δ7 for general CSPs [JPV21b] and Δ5.714 for atomic CSPs, including the special case of k-CNF [JPV21a, HSW21]. Our sampling approach departs from previous fast algorithms for sampling LLL, which were based on Markov chains. A crucial step of our algorithm is a recursive marginal sampler that is of independent interests. Within a local lemma regime, this marginal sampler can draw a random value for a variable according to its marginal distribution, at a cost independent of the size of the CSP. Copyright © 2022, The Authors. All rights reserved.

关键词： Constraint satisfaction problems

Learning Group-Disentangled Representation for Interpretable Thoracic Pathologic Prediction

学校读者我要写书评

暂无评论

Learning Group-Disentangled Representation for Interpretable...

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Hao Li Yirui Wu Hexuan Hu Hu Lu Yong Lai Shaohua Wan Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University College of Computer and Information Hohai University Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University School of Computer Science and Communication Engineering Jiangsu University Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China

ISBN: (数字)9781665468190

ISBN: (纸本)9781665468206

Deep learning methods have shown significant performance in medical image analysis tasks. However, they generally act like ”black box” without explanations in both feature extraction and decision processes, leading to lack of clinical insights and high risk assessments. To aid deep learning in envisioning diseases with visual clues, we propose Representation Group-Disentangling Network (RGD-Net), which can completely disentangle feature space of input X-ray images into several independent feature groups, each corresponding to a specific disease. Taking several semantically related and labeled X-ray images as input, RGD-Net firstly extracts completely group-disentangled representations of diseases through Group-Disentangle Module, which applies group-swap and linking operations to construct latent space by enforcing semantic consistency of attributes. To prevent learning degenerate representations defined as shortcut problem, we further introduce adversarial constricts on mapping from features to diseases, thus avoiding model collapse with former free-form disentanglement. Experiments on chestxray-14 and ChestXpert datasets demonstrate that RGD-Net are effective in predicting diseases with remarkable advantages, which leverage potential factors contributing to different diseases, thus enhancing interpretability in working patterns of deep learning methods.

关键词： Deep learning Training Visualization Image analysis Semantics Feature extraction Risk management

LSBert: Lexical Simplification Based on BERT

学校读者我要写书评

暂无评论

IEEE/ACM Transactions on Audio Speech and Language Processing 2021年 29卷 3064-3076页

作者： Qiang, Jipeng Li, Yun Zhu, Yi Yuan, Yunhao Shi, Yang Wu, Xindong Department of Computer Science Jiangsu Yangzhou China Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Ministry of Education Anhui Hefei China Mininglamp Academy of Sciences Minininglamp Beijing 100864 China

Lexical simplification (LS) aims at replacing complex words with simpler alternatives. LS commonly consists of three main steps: complex word identification, substitute generation, and substitute ranking. Existing LS methods focus on the contextual information of the complex word in the last step (substitute ranking). However, they miss out the following two facts: (1) The word complexity of a polysemous word is very closely related to its context;(2) The step of substitute generation regardless of the context will inevitably produce a large number of spurious candidates. Therefore, we propose a novel LS system LSBert based on pretrained language model BERT to address the aforementioned issues, which is capable of making use of the wider context when both identifying the words in need of simplification and generating substitute candidates for the complex words. Specifically, LSBert consists of a network for complex word identification by fine-tuning BERT and a network for substitute generation based on BERT. Experimental results show that LSBert performs well in both complex word identification and substitute generation, achieving state-of-the-art results in three benchmarks. © 2014 IEEE.

关键词： BERT Complex word identification Lexical simplification Sentence simplification

Semimetal Contacts to Monolayer Semiconductor: Weak Metalization as an Effective Mechanism to Schottky Barrier Lowering

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Su, Tong Li, Yueyan Wang, Qianqian Zhao, Weiwei Cao, Liemao Ang, Yee Sin Sauvage Laboratory for Smart Materials School of Materials Science and Engineering Harbin Institute of Technology Shenzhen518055 China Shenzhen Key Laboratory of Flexible Printed Electronics Technology Harbin Institute of Technology Shenzhen518055 China Science Mathematics and Technology Singapore University of Technology and Design Singapore487372 Singapore School of Information Management Nanjing University Nanjing210023 China Jiangsu Key Laboratory of Data Engineering and Knowledge Service Nanjing210023 China College of Physics and Electronic Engineering Hengyang Normal University Hengyang421002 China

Recent experiment has uncovered semimetal bismuth (Bi) as an excellent electrical contact to monolayer MoS2 with ultralow contact resistance. The contact physics of the broader semimetal/monolayer-semiconductor family beyond Bi/MoS2, however, remains largely unexplored thus far. Here we perform a comprehensive first-principle density functional theory investigation on the electrical contact properties between six archetypal two-dimensional (2D) transition metal dichalcogenide (TMDC) semiconductors, i.e. MoS2, WS2, MoSe2, WSe2, MoTe2 and WTe2, and two representative types of semimetals, Bi and antimony (Sb). As Bi and Sb work functions energetically aligns well with the TMDC conduction band edge, Ohmic or nearly-Ohmic n-type contacts are prevalent. The interlayer distance of semimetal/TMDC contacts are significantly larger than that of the metal/TMDC counterparts, which results in only weak metalization of TMDC upon contact formation. Intriguingly, such weak metalization generates semimetal-induced gap states (MIGS) that extends below the conduction band minimum, thus offering an effective mechanism to reduce or eliminate the n-type Schottky barrier height (SBH) while still preserving the electronic structures of 2D TMDC. A modified Schottky-Mott rule that takes into account SMIGS, interface dipole potential, and Fermi level shifting is proposed, which provides an improved agreement with the DFT-simulated SBH. We further show that the tunneling-specific resistivity of Sb/TMDC contacts are generally lower than the Bi counterparts, thus indicating a better charge injection efficiency can be achieved through Sb contacts. Our findings reveal the promising potential of Bi and Sb as excellent companion electrode materials for advancing 2D semiconductor device technology. Copyright © 2022, The Authors. All rights reserved.

关键词： Molybdenum compounds

Examining scientific writing styles from the perspective of linguistic complexity

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Lu, Chao Bu, Yi Wang, Jie Ding, Ying Torvik, Vetle Schnaars, Matthew Zhang, Chengzhi School of Economics and Management Nanjing University of Science and Technology Nanjing Jiangsu China School of Informatics Computing and Engineering Indiana University BloomingtonIN United States Center for Complex Networks and Systems Research School of Informatics Computing and Engineering Indiana University BloomingtonIN United States School of Information Management Nanjing University Nanjing Jiangsu China School of Information Management Wuhan University Wuhan Hubei China School of Information Sciences University of Illinois UrbanaIL United States Jiangsu Key Laboratory of Data Engineering and Knowledge Service Nanjing University Nanjing Jiangsu China

Publishing articles in high-impact English journals is difficult for scholars around the world, especially for non-native English-speaking scholars (NNESs), most of whom struggle with proficiency in English. In order to uncover the differences in English scientific writing between native English-speaking scholars (NESs) and NNESs, we collected a large-scale data set containing more than 150,000 full-text articles published in PLoS between 2006 and 2015. We divided these articles into three groups according to the ethnic backgrounds of the first and corresponding authors, obtained by Ethnea, and examined the scientific writing styles in English from a two-fold perspective of linguistic complexity: (1) syntactic complexity, including measurements of sentence length and sentence complexity;and (2) lexical complexity, including measurements of lexical diversity, lexical density, and lexical sophistication. The observations suggest marginal differences between groups in syntactical and lexical complexity. Copyright © 2018, The Authors. All rights reserved.

关键词：