检索结果-内蒙古大学图书馆

2nd workshop on Simple and Efficient natural language processing, SustaiNLP 2021

ISBN: (纸本)9781955917018

The proceedings contain 17 papers. The topics discussed include: low resource quadratic forms for knowledge graph embeddings;evaluating the carbon footprint of NLP methods: a survey and analysis of existing tools;limitations of knowledge distillation for zero-shot transfer learning;countering the influence of essay length in neural essay scoring;memory-efficient transformers via top-k attention;combining lexical and dense retrieval for computationally efficient multi-hop question answering;learning to rank in the age of Muppets: effectiveness–efficiency tradeoffs in multi-stage ranking;improving synonym recommendation using sentence context;semantic categorization of social knowledge for commonsense question answering;speeding up transformer training by using dataset subsampling - an exploratory analysis;and hyperparameter power impact in transformer language model training.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Online News Event Extraction for Crime Analysis 30

Online News Event Extraction for Crime Analysis

引用

30th Italian Symposium on Advanced Database Systems, SEBD 2022

作者： Rollo, Federica Po, Laura Bonisoli, Giovanni Enzo Ferrari Engineering Department University of Modena and Reggio Emilia Via Vivarelli 10 Modena Italy

Event Extraction is a complex and interesting topic in Information Extraction that includes methods for the identification of event's type, participants, location, and date from free text or web data. The result of event extraction systems can be used in several fields, such as online monitoring systems or decision support tools. In this paper, we introduce a framework that combines several techniques (lexical, semantic, machine learning, neural networks) to extract events from Italian news articles for crime analysis purposes. Furthermore, we concentrate to represent the extracted events in a Knowledge graph. An evaluation on crimes in the province of Modena is reported. © 2022 CEUR-WS. All rights reserved.

关键词： natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Story Point Level Classification by Text Level graph Neural Network

Story Point Level Classification by Text Level Graph Neural ...

引用

natural language-based Software Engineering (NLBSE), IEEE/ACM International workshop on

作者： Hung Phan Ali Jannesari Iowa State University Ames Iowa USA

ISBN: (纸本)9781665462310

Estimating the software projects’ efforts developed by agile methods is important for project managers or technical leads. It provides a summary as a first view of how many hours and developers are required to complete the tasks. There are research works on automatic predicting the software efforts, including Term Frequency - Inverse Document Frequency (TFIDF) as the traditional approach for this problem. graph Neural Network is a new approach that has been applied in natural language processing for text classification. The advantages of graph Neural Network are based on the ability to learn information via graph data structure, which has more representations such as the relationships between words compared to approaches of vectorizing sequence of words. In this paper, we show the potential and possible challenges of graph Neural Network text classification in story point level estimation. By the experiments, we show that the GNN Text Level Classification can achieve as high accuracy as about 80% for story points level classification, which is comparable to the traditional approach. We also analyze the GNN approach and point out several current disadvantages that the GNN approach can improve for this problem or other problems in software engineering.

关键词： Conferences Text categorization Estimation Data structures graph neural networks Software natural language processing

来源：评论

学校读者我要写书评

暂无评论

ExCAR: Event graph Knowledge Enhanced Explainable Causal Reasoning 59

ExCAR: Event Graph Knowledge Enhanced Explainable Causal Rea...

引用

Joint Conference of 59th Annual Meeting of the Association-for-Computational-Linguistics (ACL) / 11th International Joint Conference on natural language processing (IJCNLP) / 6th workshop on Representation Learning for NLP (RepL4NLP)

作者： Du, Li Ding, Xiao Xiong, Kai Liu, Ting Qin, Bing Harbin Inst Technol Res Ctr Social Comp & Informat Retrieval Harbin Heilongjiang Peoples R China

ISBN: (纸本)9781954085527

Prior work infers the causation between events mainly based on the knowledge induced from the annotated causal event pairs. However, additional evidence information intermediate to the cause and effect remains unexploited. By incorporating such information, the logical law behind the causality can be unveiled, and the interpretability and stability of the causal reasoning system can be improved. To facilitate this, we present an Event graph knowledge enhanced explainable CAusal Reasoning framework (ExCAR). ExCAR first acquires additional evidence information from a large-scale causal event graph as logical rules for causal reasoning. To learn the conditional probabilistic of logical rules, we propose the Conditional Markov Neural Logic Network (CMNLN) that combines the representation learning and structure learning of logical rules in an end-to-end differentiable manner. Experimental results demonstrate that ExCAR outperforms previous state-of-the-art methods. Adversarial evaluation shows the improved stability of ExCAR over baseline systems. Human evaluation shows that ExCAR can achieve a promising explainable performance.

关键词： System stability

来源：评论

学校读者我要写书评

暂无评论

Using Part-of-Speech Tagging for Building Networks of Terms in Legal Sphere 5

Using Part-of-Speech Tagging for Building Networks of Terms ...

引用

5th International Conference on Computational Linguistics and Intelligent Systems (COLINS)

作者： Lande, Dmytro Dmytrenko, Oleh NAS Ukraine IRR 2 Mykoly Shpaka St UA-03113 Kiev Ukraine NTU Igor Sikorsky KPI 37 Prosp Peremohy UA-03056 Kiev Ukraine NALS Ukraine SRIIL 110-v Saksaganskogo St UA-01032 Kiev Ukraine

This paper considers an important formalization problem and building the terminological ontology of problem subject domains based on content-related text data. As an ontological model, we propose to use a linguistic network model of text representation, the so-called network of key terms. In this network, the nodes are keywords and phrases that appear in the text corpus, and the links between them are semantic-syntactic links between these terms in the text. Using systems of aggregation of thematic information flows from freely available information resources distributed in global computer networks, input sets of text data were prepared. In particular, this paper solves the important and urgent problem of computerized processing of legal information. The task of computerized processing of natural language texts lies at the intersection between linguistic theory and mathematical sciences. Therefore, a wider natural language processing based on Part-of-Speech tagging was used for extraction of the key terms. After the extraction, a statistical weighing of the formed words and phrases was performed. The horizontal visibility graph algorithm was used to build undirected links between key terms. This paper also considers a new method that allows determining the direction of links between terms and weighting these links in the undirected network of words and phrases. This method takes into account the parts of speech tagging and also obeys the principle of inclusion of a word or phrase in their corresponding extended phrases with more words. The approbation of the proposed method was carried out on the example of a freely available legal document << Universal Declaration of Human Rights >>. After extracting the key terms from this legal document and determining the direction and weight of links between words or phrases using the proposed methods the directed weighted network of terms was built. The considered in this work method for building the terminological networks ca

关键词： Information space unstructured data ontological model problem subject domain legal information text corpus computerized text processing Part-of-Speech tagging network of terms automatic summarization

来源：评论

学校读者我要写书评

暂无评论

融合语义与结构信息的知识图谱补全模型研究

引用

数据分析与知识发现 2024年第4期8卷 39-49页

作者：马志远高颖张强周洪李兵陶皖安徽工程大学计算机与信息学院芜湖241000 华中师范大学信息管理学院武汉430079 中国科学院武汉文献情报中心武汉430071 科学技术部科技人才交流开发服务中心北京100045

【目的】针对知识图谱补全任务,挖掘语义与结构信息,完善知识图谱并提升质量与可靠性。【方法】提出一种融合语义与结构信息的知识图谱补全模型,通过预训练语言模型增强知识图谱内文本及上下文数据的嵌入表示,捕获实体与关系的语义信息... 详细信息

【目的】针对知识图谱补全任务,挖掘语义与结构信息,完善知识图谱并提升质量与可靠性。【方法】提出一种融合语义与结构信息的知识图谱补全模型,通过预训练语言模型增强知识图谱内文本及上下文数据的嵌入表示,捕获实体与关系的语义信息,并构建实体-关系矩阵映射知识图谱网络结构,获取实体的邻域信息与关系约束,进一步融合潜在数据,进行模型训练并预测丢失实体,最终达成知识图谱补全任务。【结果】与基线方法性能相比,该模型的Hits@3评测指标在FB15k-237、WN18RR和UMLS数据集上分别提升0.5、0.6和0.6个百分点。【局限】受限于语言模型的基础表示能力,未能结合多模态数据进一步提升补全任务效果。【结论】该模型具有较好的补全性能,融合语义与结构信息的方式对比其他方法具有一定优势,能够较好地完成知识图谱补全任务,对知识图谱及其下游应用的发展具有重要意义。

关键词：知识图谱补全预训练语言模型自然语言处理深度学习

来源：评论

学校读者我要写书评

暂无评论

SERAG: Semantic Entity Retrieval from Arabic knowledge graphs 6

SERAG: Semantic Entity Retrieval from Arabic knowledge Graph...

引用

6th Arabic natural language processing workshop, WANLP 2021

作者： Esmeir, Saher Bloomberg L.P. London United Kingdom

ISBN: (纸本)9781954085091

Knowledge graphs (KGs) are widely used to store and access information about entities and their relationships. Given a query, the task of entity retrieval from a KG aims at presenting a ranked list of entities relevant to the query. Lately, an increasing number of models for entity retrieval have shown a significant improvement over traditional methods. These models, however, were developed for English KGs. In this work, we build on one such system, named KEWER, to propose SERAG (Semantic Entity Retrieval from Arabic knowledge graphs). Like KEWER, SERAG uses random walks to generate entity embeddings. DBpedia-Entity v2 is considered the standard test collection for entity retrieval. We discuss the challenges of using it for non-English languages in general and Arabic in particular. We provide an Arabic version of this standard collection, and use it to evaluate SERAG. SERAG is shown to significantly outperform the popular BM25 model thanks to its multi-hop reasoning. © WANLP 2021 - 6th Arabic natural language processing workshop

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

A Chinese Entity-Relation Extraction Method Via Improved Machine Reading Comprehension 4

A Chinese Entity-Relation Extraction Method Via Improved Mac...

引用

4th International Conference on Intelligent Information processing, IIP 2022

作者： Shang, Tianci Deng, Baosong Jiang, Tingsong Defense Innovation Institute Chinese Academy of Military Science Beijing100071 China

ISBN: (纸本)9781665492225

As the downstream task of building a knowledge graph, Chinese entity relationship extraction from unstructured texts plays an important role in the field of natural language processing. There are two main ways for Chinese entity relation extraction: joint extraction method and pipeline extraction method. The joint extraction method outputs the relation triples contained in the texts directly in a row, which causes two problems: the lack of external knowledge and the nesting of entities. This article proposes a method to take the advantage of the similarity between the span extraction task and the information extraction task, and transforms entity relation extraction problem into a task similar to machine reading comprehension. This method first uses the Roberta pre-training model to obtain word representation with relation information, and then identifies entity pairs that may exists under per relation through a global pointer network, which outperforms better than the normal pointer network. By comparing different models' performance on the same dataset, the results show the accuracy, recall and F1 scores of our method are higher than other methods, which proves the effectiveness of our method. © 2022 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

YNU-HPCC at SemEval-2021 Task 11: Using a BERT Model to Extract Contributions from NLP Scholarly Articles 15

YNU-HPCC at SemEval-2021 Task 11: Using a BERT Model to Extr...

引用

15th International workshops on Semantic Evaluation (SemEval)

作者： Ma, Xinge Wang, Jin Zhang, Xuejie Yunnan Univ Sch Informat Sci & Engn Kunming Yunnan Peoples R China

ISBN: (纸本)9781954085701

This paper describes the system we built as the YNU-HPCC team in the SemEval-2021 Task 11: NLPContributiongraph. This task involves first identifying sentences in the given natural language processing (NLP) scholarly articles that reflect research contributions through binary classification;then identifying the core scientific terms and their relation phrases from these contribution sentences by sequence labeling;and finally, these scientific terms and relation phrases are categorized, identified, and organized into subject-predicateobject triples to form a knowledge graph with the help of multiclass classification and multilabel classification. We developed a system for this task using a pre-trained language representation model called BERT that stands for Bidirectional Encoder Representations from Transformers, and achieved good results. The average F-1-score for Evaluation Phase 2, Part 1 was 0.4562 and ranked 7th, and the average F-1-score for Evaluation Phase 2, Part 2 was 0.6541, and also ranked 7th.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous graph Neural Networks for Keyphrase Generation

Heterogeneous Graph Neural Networks for Keyphrase Generation

引用

Conference on Empirical methods in natural language processing (EMNLP)

作者： Ye, Jiacheng Cai, Ruijian Gui, Tao Zhang, Qi Fudan Univ Shanghai Key Lab Intelligent Informat Proc Sch Comp Sci Shanghai Peoples R China Fudan Univ Inst Modern Languages & Linguist Shanghai Peoples R China

ISBN: (纸本)9781955917094

The encoder-decoder framework achieves state-of-the-art results in keyphrase generation (KG) tasks by predicting both present keyphrases that appear in the source document and absent keyphrases that do not. However, relying solely on the source document can result in generating uncontrollable and inaccurate absent keyphrases. To address these problems, we propose a novel graph-based method that can capture explicit knowledge from related references. Our model first retrieves some document-keyphrases pairs similar to the source document from a pre-defined index as references. Then a heterogeneous graph is constructed to capture relationships of different granularities between the source document and its references. To guide the decoding process, a hierarchical attention and copy mechanism is introduced, which directly copies appropriate words from both the source document and its references based on their relevance and significance. The experimental results on multiple KG benchmarks show that the proposed model achieves significant improvements against other baseline models, especially with regard to the absent keyphrase prediction.

关键词： graph neural networks

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：