检索结果-内蒙古大学图书馆

7th International Conference on Advances in Computing, Communications and Informatics, ICACCI 2018

作者： Varalakshmi K, P.N. Kallimani, Jagadish S. Department of Computer Science and Engineering M S Ramaiah Institute of Technology India

ISBN: (纸本)9781538653142

Text summarization has been one of the key research areas in natural language processing (NLP) for a while. The various methods to summarize one or more documents can be broadly classified into extractive and abstractive text summarization where the former involves selecting key parts in the document and embedding into the summary while balancing between salience and redundancy. The latter involves creating new sentences to provide a summary of the documents. Extractive summarization can further be done in a supervised manner with humans or an unsupervised manner without any human intervention. This paper provides the knowledge a few of the current methods to perform extractive text summarization where the input would be multi document sets. Multi document summarization can consider two types of document sets;a homogeneous set of documents which have a common topic or theme and a heterogeneous set where the main topic for the documents are unrelated but they contain some form information that is related to the summary. The first method uses sentence regression where they consider performing sentence ranking along with sentence relations followed by greedy selection process. The second is an unsupervised paragraph embedding method utilizing a density peaks clustering method. The third method proposes document-level reconstruction using a neural document model. The fourth method is a query focused, joint neural network based model with an attention mechanism. The fifth method concentrates on coherence by providing a graph-based model which does not require discourse analysis as a prerequisite. We also see a way to create a heterogeneous multi-documentcorpus along with the limitations of each of these methods. © 2018 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Analyzing transfer learning impact in biomedical cross-lingual named entity recognition and normalization

引用

BMC BIOINFORMATICS 2021年第SUPPL 1期22卷 601-601页

作者： Rivera-Zavala, Renzo M. Martinez, Paloma Univ Carlos III Madrid Comp Sci Dept Madrid Spain

Background The volume of biomedical literature and clinical data is growing at an exponential rate. Therefore, efficient access to data described in unstructured biomedical texts is a crucial task for the biomedical industry and research. Named Entity Recognition (NER) is the first step for information and knowledge acquisition when we deal with unstructured texts. Recent NER approaches use contextualized word representations as input for a downstream classification task. However, distributed word vectors (embeddings) are very limited in Spanish and even more for the biomedical domain. methods In this work, we develop several biomedical Spanish word representations, and we introduce two Deep Learning approaches for pharmaceutical, chemical, and other biomedical entities recognition in Spanish clinical case texts and biomedical texts, one based on a Bi-STM-CRF model and the other on a BERT-based architecture. Results Several Spanish biomedical embeddigns together with the two deep learning models were evaluated on the PharmaCoNER and CORD-19 datasets. The PharmaCoNER dataset is composed of a set of Spanish clinical cases annotated with drugs, chemical compounds and pharmacological substances;our extended Bi-LSTM-CRF model obtains an F-score of 85.24% on entity identification and classification and the BERT model obtains an F-score of 88.80% . For the entity normalization task, the extended Bi-LSTM-CRF model achieves an F-score of 72.85% and the BERT model achieves 79.97%. The CORD-19 dataset consists of scholarly articles written in English annotated with biomedical concepts such as disorder, species, chemical or drugs, gene and protein, enzyme and anatomy. Bi-LSTM-CRF model and BERT model obtain an F-measure of 78.23% and 78.86% on entity identification and classification, respectively on the CORD-19 dataset. Conclusion These results prove that deep learning models with in-domain knowledge learned from large-scale datasets highly improve named entity recognition per

关键词： natural language processing Clinical texts Deep learning Contextual information

来源：评论

学校读者我要写书评

暂无评论

基于知识图谱、TF-IDF和BERT模型的冬奥知识问答系统

引用

智能系统学报 2021年第4期16卷 819-826页

作者：罗玲李硕凯何清杨骋骐王宇洋恒陈天宇中国科学院计算技术研究所智能信息处理重点实验室北京100190 中国科学院大学北京100049

传统信息检索技术已经不能满足人们对信息获取效率的要求,智能问答系统应运而生,并成为自然语言处理领域一个非常重要的研究热点。本文针对中文的冬奥问答领域,提出了基于知识图谱、词频-逆文本频率指数(term frequency-inverse documen... 详细信息

传统信息检索技术已经不能满足人们对信息获取效率的要求,智能问答系统应运而生,并成为自然语言处理领域一个非常重要的研究热点。本文针对中文的冬奥问答领域,提出了基于知识图谱、词频-逆文本频率指数(term frequency-inverse document frequency,TF-IDF)和自注意力机制的双向编码表示(bidirectional encoder representation from transformers,BERT)的3种冬奥问答系统模型。本文首次构建了冬奥问答数据集,并将上述3种方法集成在一起,应用于冬奥问答领域,用户可以使用本系统来快速准确地获取冬奥内容相关的问答知识。进一步,对3种模型的效果进行了测评,测量了3种模型各自的回答可接受率。实验结果显示BERT模型的整体效果略优于知识图谱和TDIDF模型,BERT模型对3类问题的回答可接受率都超过了96%,知识图谱和TDIDF模型对于复合统计问答对的回答效果不如BERT模型。

关键词：智能问答冬奥问答对话模型知识图谱 TF-IDF BERT

来源：评论

学校读者我要写书评

暂无评论

Construction of a Linked Data Set of COVID-19 Knowledge graphs: Development and Applications

引用

JMIR MEDICAL INFORMATICS 2022年第5期10卷 e37215页

作者： Wang, Haofen Du, Huifang Qi, Guilin Chen, Huajun Hu, Wei Chen, Zhuo Tongji Univ Coll Design & Innovat 281 Fuxin Rd Shanghai 200092 Peoples R China Southeast Univ Sch Comp Sci & Engn Nanjing Peoples R China Zhejiang Univ Coll Comp Sci & Technol Hangzhou Peoples R China Nanjing Univ Natl Inst Healthcare Data Sci Nanjing Peoples R China

Background: With the continuous spread of COVID-19, information about the worldwide pandemic is exploding. Therefore, it is necessary and significant to organize such a large amount of information. As the key branch of artificial intelligence, a knowledge graph (KG) is helpful to structure, reason, and understand data. Objective: To improve the utilization value of the information and effectively aid researchers to combat COVID-19, we have constructed and successively released a unified linked data set named OpenKG-COVID19, which is one of the largest existing KGs related to COVID-19. OpenKG-COVID19 includes 10 interlinked COVID-19 subgraphs covering the topics of encyclopedia, concept, medical, research, event, health, epidemiology, goods, prevention, and character. methods: In this paper, we introduce the key techniques exploited in building COVID-19 KGs in a top-down manner. first, the schema of the modeling process for each KG in OpenKG-COVID19 is described. Second, we propose different methods for extracting knowledge from open government sites, professional texts, public domain-specific sources, and public encyclopedia sites. The curated 10 COVID-19 KGs are further linked together at both the schema and data levels. In addition, we present the naming convention for OpenKG-COVID19. Results: OpenKG-COVID19 has more than 2572 concepts, 329,600 entities, 513 properties, and 2,687,329 facts, and the data set will be updated continuously. Each COVID-19 KG was evaluated, and the average precision was found to be above 93%. We have developed search and browse interfaces and a SPARQL endpoint to improve user access. Possible intelligent applications based on OpenKG-COVID19 for further development are also described. Conclusions: A KG is useful for intelligent question-answering, semantic searches, recommendation systems, visualization analysis, and decision-making support. Research related to COVID-19, biomedicine, and many other communities can benefit from OpenKG-COV

关键词： knowledge graph linked data COVID-19 knowledge extraction knowledge fusion natural language processing artificial intelligence data set schema modeling semantic search

来源：评论

学校读者我要写书评

暂无评论

Hybrid Approach to Crime Prediction using Deep learning

Hybrid Approach to Crime Prediction using Deep learning

引用

International Conference on Advances in Computing, Communications and Informatics

作者： Jazeem Azeez D. John Aravindhar Department of Computer Science & Engineering Hindustan Institute of Technology & Science

ISBN: (纸本)9781479987931

Prevention is better that Cure. Preventing a crime from occurring is better than investigating what or how the crime had occurred. Just like vaccination is given to a child to prevent disease, in today's world with such higher crime rate and brutal crime happenings, it have become necessary to have a vaccination systems that prevents from crimes happening. By vaccinating society against crime it refers to various methods such as educating peoples, creating awareness, increasing efficiency and proactive policing methods and other deterrent techniques. Inspired by two different existing approach to crime prediction, the first one present a visual analytics approach that provides decision makers with a proactive and predictive environment in order to assist them in making effective resource allocation and deployment decisions. Crime incident prediction has depends mainly on the historical crime record and various geospatial and demographic information. Even though it's promising, they do not take into account the rich and rapidly expanding social & web media context that surrounds incidents of interest. Next approach is based on the semantic analysis and natural language processing of Twitter posts via latent Dirichlet allocation, Topic detection & Sentiment analysis. But both the techniques faces inherent limitations. Crime that happens these days are have following key characteristics such as crimes repeating in a periodic fashion, crimes occurring as a result of some other activity and occurrence of crimes pre indicated by some other information.

关键词： Deep Learning STL Sentiment Analysis LDA Undirected Probabilistic graph RNN

来源：评论

学校读者我要写书评

暂无评论

FAITHFUL EXPLANATIONS OF BLACK-BOX NLP MODELS USING LLM-GENERATED COUNTERFACTUALS

arXiv

引用

arXiv 2023年

作者： Gat, Yair Ori Calderon, Nitay Feder, Amir Chapanin, Alexander Sharma, Amit Reichart, Roi Faculty of Data and Decision Sciences Technion IIT Columbia University Data Science Institute United States Microsoft Research India India

Causal explanations of the predictions of NLP systems are essential to ensure safety and establish trust. Yet, existing methods often fall short of explaining model predictions effectively or efficiently and are often model-specific. In this paper, we address model-agnostic explanations, proposing two approaches for counterfactual (CF) approximation. The first approach is CF generation, where a large language model (LLM) is prompted to change a specific text concept while keeping confounding concepts unchanged. While this approach is demonstrated to be very effective, applying LLM at inference-time is costly. We hence present a second approach based on matching, and propose a method that is guided by an LLM at training-time and learns a dedicated embedding space. This space is faithful to a given causal graph and effectively serves to identify matches that approximate CFs. After showing theoretically that approximating CFs is required in order to construct faithful explanations, we benchmark our approaches and explain several models, including LLMs with billions of parameters. Our empirical results demonstrate the excellent performance of CF generation models as model-agnostic explainers. Moreover, our matching approach, which requires far less test-time resources, also provides effective explanations, surpassing many baselines. We also find that Top-K techniques universally improve every tested method. Finally, we showcase the potential of LLMs in constructing new benchmarks for model explanation and subsequently validate our conclusions. Our work illuminates new pathways for efficient and accurate approaches to interpreting NLP systems. © 2023, CC0.

关键词： natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Exploiting Visual Relation and Multi-Grained Knowledge for Multimodal Relation Extraction

Exploiting Visual Relation and Multi-Grained Knowledge for M...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Qianru Shen Hailun Lin Huan Liu Zheng Lin Weiping Wang Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Cyberspace Security Defense Beijing China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Given a text and its related image, the multimodal relation extraction (MRE) task aims at predicting the correct semantic relation between two entities in the input text. Though certain advances have been made by recent MRE approaches, they still suffer from two drawbacks. first, they ignore fine-grained visual relations between image objects which can serve as important clues for inferring the correct relation. Second, they are unable to utilize useful external knowledge about entities and the input sentence, leading to a sub-optimal performance when processing examples that demand related background or commonsense knowledge. To alleviate above limitations, we propose a novel method, named VRMK, which exploits both Visual Relations and Multi-grained Knowledge for the MRE task. Specifically, the input image-text pair is converted into a unified multimodal graph. Then, the relation-aware transformer is adopted to update node representations while explicitly encoding diverse relations among visual and textual nodes. based on the input text, the powerful large language model (LLM) is used to generate entity-level and sentence-level knowledge with the in-context learning. The most relevant knowledge information is captured by a cross-attention mechanism and is further combined with the representations of entity nodes and original text to predict the final relation label. On the MNRE dataset, VRMK outperforms recent state-of-the-art baselines including LLM-based methods by 2.71% (82.55%→85.26% in F1 score). We also conduct extensive ablation experiments to reveal contributions of different modules and provide useful insights for future research.

关键词： Knowledge engineering Visualization Large language models Aggregates Semantics Neural networks Knowledge graphs

来源：评论

学校读者我要写书评

暂无评论

面向中文的字词组合序列实体识别方法

引用

清华大学学报（自然科学版） 2023年第9期63卷 1326-1338页

作者：王庆人王银子仲红张以文安徽大学计算机科学与技术学院合肥230093

作为信息抽取的核心任务,命名实体识别能够从文本中识别不同类型命名实体。得益于深度学习在字词表示、特征提取方面的应用,中文命名实体识别任务取得了丰富研究成果。然而,中文命名实体识别任务依旧面临词汇信息缺乏的挑战,主要表现为... 详细信息

作为信息抽取的核心任务,命名实体识别能够从文本中识别不同类型命名实体。得益于深度学习在字词表示、特征提取方面的应用,中文命名实体识别任务取得了丰富研究成果。然而,中文命名实体识别任务依旧面临词汇信息缺乏的挑战,主要表现为:1)词汇边界信息和上下文语义信息未充分利用;2)字和自匹配词汇间语义信息未能有效捕获;3)图注意力网络输出信息中不同交互图信息的重要性未被考虑。该文提出一种面向中文的字词组合序列实体识别方法。采用字词组合序列嵌入结构,实现词汇边界信息以及字符与词汇间语义信息的充分捕捉;采用多图注意力融合架构,实现不同图神经网络提取特征重要性的区分。实验表明,相比已有经典方法,该方法在Weibo、Resume、OntoNotes4.0及MSRA四个数据集上的F1明显提升,在中文命名实体识别任务上具有可行性。

关键词：自然语言处理命名实体识别图注意力网络字词组合嵌入多图注意力

来源：评论

学校读者我要写书评

暂无评论

State Space Model for New-Generation Network Alternative to Transformers: A Survey

arXiv

引用

arXiv 2024年

作者： Wang, Xiao Wang, Shiao Ding, Yuhe Li, Yuehang Wu, Wentao Rong, Yao Kong, Weizhe Huang, Ju Li, Shihao Yang, Haoxiang Wang, Ziwen Jiang, Bo Li, Chenglong Wang, Yaowei Tian, Yonghong Tang, Jin School of Computer Science and Technology Anhui University Hefei230601 China School of Artificial Intelligence Anhui University Hefei230601 China Peng Cheng Laboratory Shenzhen China Harbin Institute of Technology [HITSZ Shenzhen China National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China School of Electronic and Computer Engineering Shenzhen Graduate School Peking University China

In the post-deep learning era, the Transformer architecture has demonstrated its powerful performance across pre-trained big models and various downstream tasks. However, the enormous computational demands of this architecture have deterred many researchers. To further reduce the complexity of attention models, numerous efforts have been made to design more efficient methods. Among them, the State Space Model (SSM), as a possible replacement for the self-attention based Transformer model, has drawn more and more attention in recent years. In this paper, we give the first comprehensive review of these works and also provide experimental comparisons and analysis to better demonstrate the features and advantages of SSM. Specifically, we first give a detailed description of principles to help the readers quickly capture the key ideas of SSM. After that, we dive into the reviews of existing SSMs and their various applications, including natural language processing, computer vision, graph, multi-modal and multi-media, point cloud/event stream, time series data, and other domains. In addition, we give statistical comparisons and analysis of these models and hope it helps the readers to understand the effectiveness of different structures on various tasks. Then, we propose possible research points in this direction to better promote the development of the theoretical model and application of SSM. More related works will be continuously updated on the following GitHub https://***/Event-AHU/Mamba_State_Space_Model_Paper_List. Copyright © 2024, The Authors. All rights reserved.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Large-scale directional relationship extraction and resolution

引用

BMC BIOINFORMATICS 2008年第Sup9期9卷 1-13页

作者： Giles, Cory B. Wren, Jonathan D. Oklahoma Med Res Fdn Arthritis & Immunol Res Program Oklahoma City OK 73104 USA

Background: Relationships between entities such as genes, chemicals, metabolites, phenotypes and diseases in MEDLINE are often directional. That is, one may affect the other in a positive or negative manner. Detection of causality and direction is key in piecing pathways together and in examining possible implications of experimental results. Because of the size and growth of biomedical literature, it is increasingly important to be able to automate this process as much as possible. Results: Here we present a method of relation extraction using dependency graph parsing with SVM classification. We tested the SVM classifier first on gold standard corpora from GENIA and find it achieved 82% precision and 94.8% recall (F-measure of 87.9) on these standardized test sets. We then applied the entire system to all available MEDLINE abstracts for two target interactions with known effects. We find that while some directional relations are extracted with low ambiguity, others are apparently contradictory, at least when considered in an isolated context. When examined, it is apparent some are dependent upon the surrounding context (e. g. whether the relationship referred to short-term or long-term effects, or whether the focus was extracellular versus intracellular). Conclusion: Thesaurus-based directional relation extraction can be done with reasonable accuracy, but is prone to false-positives on larger corpora due to noun modifiers. Furthermore, methods of resolving or disambiguating relationship context and contingencies are important for large-scale corpora.

关键词： Support Vector Machine Caffeine natural language processing Dependency Path Query Term

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：