检索结果-内蒙古大学图书馆

knowledge-enhanced attentive learning for answer selection in community question answering systems

knowledge-BASED SYSTEMS 2022年第0期250卷

作者： Jing, Fengshi Ren, Hao Cheng, Weibin Wang, Xin Zhang, Qingpeng Guangdong Second Prov Gen Hosp Inst Healthcare Artificial Intelligence Guangzhou 510317 Peoples R China City Univ Hong Kong Sch Data Sci Hong Kong Peoples R China Univ North Carolina Chapel Hill Sch Med UNC Project China UNC Global China NC USA Tianjin Univ Coll Intelligence & Comp Sch Artificial Intelligence Tianjin Peoples R China Tianjin Key Lab Cognit Comp & Applicat Tianjin Peoples R China

In a community question-answering (CQA) system, the answer selection task is used to identify the best answer for a specific question. This plays a key role in improving service quality by recommending appropriate answers to new questions. Recent advances in CQA answer selection have focused on enhancing performance by incorporating community information, and particularly the expertise (previous answers) and authority (position in the social network) of a respondent. However, existing approaches to incorporating this information are limited, as they (a) consider either the expertise or the authority, but not both;(b) ignore domain knowledge that could differentiate between the topics of previous answers;or (c) simply use authority information to adjust the similarity score, rather than fully integrating it into the process of measuring the similarity between the question and answer segments. We propose a new approach called the knowledge-enhanced attentive answer selection (KAAS) model, which enhances performance by (a) considering both the expertise and the authority of the answerer;(b) utilizing human-labeled tags, a taxonomy of tags, and votes as domain knowledge to infer the expertise of the respondent;(c) using a matrix decomposition of the social network (based on 'following' relationships) to infer the authority of the respondent and incorporating this information into the process of evaluating the similarity between segments. In addition, we incorporate an external knowledge graph to capture more professional information for CQA systems for vertical communities. We also adopt an attention mechanism to integrate our analysis of both questions and answers texts and the aforementioned community information. Experiments with both vertical and general CQA sites demonstrate the superior performance of the proposed KAAS model. (c) 2022 Elsevier B.V. All rights reserved.

关键词： knowledge discovery Answer selection Recommender systems Community question answering knowledge graph embedding

来源：评论

学校读者我要写书评

暂无评论

Three birds, one stone: A novel translation based framework for joint entity and relation extraction

引用

knowledge-BASED SYSTEMS 2022年第0期236卷 107677-107677页

作者： Huang, Heyan Shang, Yu-Ming Sun, Xin Wei, Wei Mao, Xianling Beijing Inst Technol Sch Comp Sci & Technol Beijing 100081 Peoples R China Beijing Engn Res Ctr High Volume Language Informa Beijing 100081 Peoples R China Huazhong Univ Sci & Technol Sch Comp Sci Wuhan 430074 Peoples R China

Joint entity and relation extraction is an important task in natural language processing and knowledge graph construction. Existing studies mainly focus on three issues: redundant predictions, overlapping triples and relation connections. However, as far as we know, none of them is able to solve the three problems simultaneously in a unified architecture. To address this issue, in this paper, we propose a novel translation based unified framework. Specifically, the proposed framework contains two components: an entity tagger and a relation extractor. The former is used to recognize all candidate head entities and tail entities respectively. The latter predicts relations for every entity pair dynamically through ranking with translation mechanism. To show the superiority of the proposed framework, we instantiate it through the simplest binary entity tagger and TransE algorithm. Extensive experiments over two widely used datasets demonstrate that, even with the simplest components, the proposed framework can still achieve competitive performance with most previous baselines. Moreover, the framework is flexible. It enjoys further performance boost when employing more powerful entity tagger and knowledge graph embedding algorithm. (c) 2021 Elsevier B.V. All rights reserved.

关键词： Entity and relation extraction Overlapping triples Redundant predictions Relation connections knowledge graph embedding

来源：评论

学校读者我要写书评

暂无评论

An explainable recommendation framework based on an improved knowledge graph attention network with massive volumes of side information

引用

knowledge-BASED SYSTEMS 2022年 239卷 107970-107970页

作者： Shimizu, Ryotaro Matsutani, Megumi Goto, Masayuki Waseda Univ Grad Sch Creat Sci & Engn 3-4-1 OhkuboShinjuku Ku Tokyo 1698555 Japan ZOZO Res Kioi Tower 22F1-3 KioichoChiyoda ku Tokyo 1020094 Japan Waseda Univ Sch Creat Sci & Engn 3-4-1 OhkuboShinjuku Ku Tokyo 1698555 Japan

In recent years, explainable recommendation has been a topic of active study. This is because the branch of the machine learning field related to methodologies is enabling human understanding of the reasons for the outputs of recommender systems. The realization of explainable recommendation is widely expected to increase both user satisfaction and the demand for explainable recommendation systems. Explainable recommendation utilizes a wealth of side information (such as sellers, brands, user ages and genders, and bookmark information, among others) to expound the decision-making reasoning applied by recommendation models. In explainable recommendation, although learning side information containing numerous variables leads to rich interpretability, learning too many variables presents a challenge because decreases the amount of learning that a given computational resource can perform, and the accuracy of the recommendation model may be degraded. However, numerous and diverse variables are included in the side information stored by the actual companies operating massive real-world services. Hence, to realize practical applications of this valuable information, it is necessary to resolve problems such as computational cost. In this study, we propose a new framework for explainable recommendation based on an improved knowledge graph attention network model, which utilizes the side information of items and realizes high recommendation accuracy. The proposed framework enables direct interpretation by visualizing the reasons for the recommendations provided. Experimental results show that the proposed framework reduced computational time requirements by approximately 80%, while maintaining recommendation accuracy by enabling the model to learn the probabilistically given edges included in the graph structure. Moreover, the results show that the proposed framework exhibited richer interpretability than the conventional model. Finally, a multifaceted analysis suggests that

关键词： Explainable artificial intelligence Explainable recommendation Model-intrinsic approach knowledge graph attention network knowledge graph embedding

来源：评论

学校读者我要写书评

暂无评论

Symbiosis: A Novel Framework for Integrating Hierarchies from knowledge graph into Recommendation System 14th

Symbiosis: A Novel Framework for Integrating Hierarchies fro...

引用

14th International Conference on knowledge Science, Engineering, and Management (KSEM)

作者： Du, Haizhou Tang, Yue Shanghai Univ Elect Power Sch Comp Sci & Technol Shanghai Peoples R China

ISBN: (纸本)9783030821364;9783030821357

Integrating knowledge graphs into recommendation systems is promising as knowledge graphs can be side information to address cold start and data sparsity issues in recommendation systems. However, existing methods largely assume that knowledge graphs are under a closed-world assumption, this may lead to suboptimal performances. Furthermore, many existing approaches fail to model semantic hierarchies, which are common in real-world applications. Therefore, it is crucial to consider the incomplete nature of knowledge graphs as well as to represent hierarchical structure when incorporating it into recommendation system. In this paper, we propose Symbiosis, which is an end-to-end model that utilizes link prediction task in knowledge graphs to assist recommendation task. A general motivation for Symbiosis is that the two tasks automatically share the latent features between items and entities. We also incorporated a hierarchical structure method that maps entities into the polar coordinate system into the Symbiosis. Under this framework, not only users can get better recommendations but also knowledge graphs can be completed as these two tasks have a mutual effect. To evaluate the performance of each component, we conduct extensive experiments with two real-world datasets from different scenarios. The extensive results show that Symbiosis can be trained substantially improving F1-score by 59.7% on movie dataset and MR by 59.3% on music dataset compared to state-of-the-art methods.

关键词： Recommendation systems knowledge graph embedding Hierarchical structure Collaborative joint learning Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Structure-Augmented Text Representation Learning for Efficient knowledge graph Completion 21

Structure-Augmented Text Representation Learning for Efficie...

引用

30th World Wide Web Conference (WWW)

作者： Wang, Bo Shen, Tao Long, Guodong Zhou, Tianyi Wang, Ying Chang, Yi Jilin Univ Sch Artificial Intelligence Changchun Jilin Peoples R China Univ Technol Sydney Sch CS Australian AI Inst FEIT Sydney NSW Australia Univ Washington Paul G Allen Sch Comp Sci & Engn Seattle WA 98195 USA Jilin Univ Coll Comp Sci & Technol Changchun Jilin Peoples R China Jilin Univ Int Ctr Future Sci Changchun Jilin Peoples R China

ISBN: (纸本)9781450383127

Human-curated knowledge graphs provide critical supportive information to various natural language processing tasks, but these graphs are usually incomplete, urging auto-completion of them (a.k.a. knowledge graph completion). Prevalent graph embedding approaches, e.g., TransE, learn structured knowledge via representing graph elements (i.e., entities/relations) into dense embeddings and capturing their triple-level relationship with spatial distance. However, they are hardly generalizable to the elements never visited in training and are intrinsically vulnerable to graph incompleteness. In contrast, textual encoding approaches, e.g., KG-BERT, resort to graph triple's text and triple-level contextualized representations. They are generalizable enough and robust to the incompleteness, especially when coupled with pre-trained encoders. But two major drawbacks limit the performance: (1) high overheads due to the costly scoring of all possible triples in inference, and (2) a lack of structured knowledge in the textual encoder. In this paper, we follow the textual encoding paradigm and aim to alleviate its drawbacks by augmenting it with graph embedding techniques - a complementary hybrid of both paradigms. Specifically, we partition each triple into two asymmetric parts as in translation-based graph embedding approach, and encode both parts into contextualized representations by a Siamese-style textual encoder. Built upon the representations, our model employs both deterministic classifier and spatial measurement for representation and structure learning respectively. It thus reduces the overheads by reusing graph elements' embeddings to avoid combinatorial explosion, and enhances structured knowledge by exploring the spatial characteristics. Moreover, we develop a self-adaptive ensemble scheme to further improve the performance by incorporating triple scores from an existing graph embedding model. In experiments, we achieve state-of-the-art performance on three benchmar

关键词： knowledge graph Completion Link Prediction knowledge graph embedding Contextualized Representation Structured knowledge

来源：评论

学校读者我要写书评

暂无评论

Relation-Aware Neighborhood Aggregation for Cross-lingual Entity Alignment 24

Relation-Aware Neighborhood Aggregation for Cross-lingual En...

引用

24th IEEE International Conference on Information Fusion (FUSION)

作者： Liu, Yuanna Geng, Jie Deng, Xinyang Jiang, Wen Northwestern Polytech Univ Sch Elect & Informat Xian Peoples R China

ISBN: (纸本)9781737749714

Cross-lingual entity alignment refers to linking entities in different language knowledge graphs if they are of identical meaning. Recent works focus on learning structure information of knowledge graphs and calculate the distance of entity embeddings for entity alignment. However, the GCN-based methods may bring noise from neighbors due to the heterogeneity of knowledge graphs. Besides, relations, as inherent attribute of knowledge graph, should be merged into the structure learning. In this paper, a relation-aware neighborhood aggregation model RANA is proposed to solve cross-lingual entity alignment task. The specific relation semantics are modeled to modify the aggregation weights of neighbors. CSLS and knowledge graph completion are introduced to enhance the alignment metric and structural information respectively. Experiments on real-world datasets demonstrate that RANA significantly outperforms other baselines in alignment accuracy and robustness.

关键词： knowledge graph embedding Entity alignment Relation-aware graph attention network

来源：评论

学校读者我要写书评

暂无评论

KIDNet: A knowledge-Aware Neural Network Model for Academic Performance Prediction

KIDNet: A Knowledge-Aware Neural Network Model for Academic ...

引用

IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT)

作者： Tang, Tao Hou, Jie Guo, Teng Bai, Xiaomei Tian, Xue Hoshyar, Azadeh Noori Federat Univ Australia Sch Engn IT & Phys Sci Ballarat Vic Australia Dalian Univ Technol Sch Software Dalian Liaoning Peoples R China Anshan Normal Univ Comp Ctr Anshan Liaoning Peoples R China Univ Tasmania Sch Arts Law & Educ Launceston Tas Australia Federat Univ Australia Sch Engn IT & Phys Sci Brisbane Qld Australia

ISBN: (纸本)9781450391870

Academic performance prediction and analysis in educational data mining is meaningful for instructors to know the student's ongoing learning status, and also provide appropriate help to students as early as possible if academic difficulties appear. In this paper, we first collect the basic information of students and courses as features. Then, we propose a novel knowledge extraction framework to obtain course knowledge features to reinforce feature groups. The comparative analyses of the knowledge similarity and average grades of the courses in all terms demonstrate a strong correlation between them. Furthermore, we build the knowledge Interaction Discovery Network (KIDNet) model, based on factorization machine (FM) and deep neural network (DNN) algorithms. This model uses FM to model lower-order interactions of sparse features and employs DNN to model higher-order interactions of both dense and sparse features. The effectiveness of KIDNet has been validated by conducting experiments based on a real-world dataset.

关键词： Educational Data Academic Prediction knowledge graph embedding knowledge Interaction

来源：评论

学校读者我要写书评

暂无评论

Entity Alignment Between knowledge graphs Using Entity Type Matching 14th

Entity Alignment Between Knowledge Graphs Using Entity Type ...

引用

14th International Conference on knowledge Science, Engineering, and Management (KSEM)

作者： Song, Xiuting Zhang, Han Bai, Luyi Northeastern Univ Qinhuangdao Sch Comp & Commun Engn Qinhuangdao 066004 Hebei Peoples R China

ISBN: (纸本)9783030821364;9783030821357

The task of entity alignment between knowledge graphs (KGs) aims to find entities in two knowledge graphs that represent the same real-world entity. Recently, embedding-based entity alignment methods get extended attention. Most of them firstly embed the entities in low dimensional vectors space via relation structure, and then align entities via these learned embeddings combined with some entity similarity function. Even achieved promising performances, these methods are inadequate in utilizing entity type information. In this paper, we propose a novel entity alignment framework, which integrates entity embeddings and entity type information to achieve entity alignment. This framework uses encoding functions to extract the type features of entities for type matching, and combines the similarity of entity embeddings to improve the accuracy of entity alignment. Our experimental results on several real-world datasets shows that our proposed method achieves improvements on entity alignment compared with most methods, and is close to the state-of-the-art method on several metrics.

关键词： Entity alignment Entity type Iterative alignment knowledge graph embedding knowledge fusion Relation triples

来源：评论

学校读者我要写书评

暂无评论

A novel Data-Driven framework based on BIM and knowledge graph for automatic model auditing and Quantity Take-off

引用

ADVANCED ENGINEERING INFORMATICS 2022年第0期54卷

作者： Liu, Hao Cheng, Jack C. P. Gan, Vincent J. L. Zhou, Shanjing Hong Kong Univ Sci & Technol Dept Civil & Environm Engn Hong Kong 999077 Peoples R China Natl Univ Singapore Dept Built Environm Singapore 117566 Singapore Imperial Coll London Ctr Syst Engn & Innovat Dept Civil & Environm Engn London SW7 2AZ England

Model auditing is a critical step before conducting Building Information Modeling (BIM)-based Quantity Take-off (QTO) because these models may contain various human errors and mistakes, leading to insufficient semantic information and inconsistent modeling style in BIM models. The traditional object-oriented approach has diffi-culties in representing unstructured BIM data (e.g., interrelationships), while rule-based methods involve tremendous human efforts to develop rule sets, lacking flexibility for different requirements. Therefore, this study aims to establish a novel data-driven framework based on BIM and knowledge graph (KG) to represent un-structured BIM data for automatic inferences of auditing results of BIM model mistakes. It starts by establishing a BIM-KG data model via identifying required information for auditing purposes. Subsequently, BIM data is automatically transformed into the BIM-KG representations, the embeddings of which are trained using a knowledge graph embedding model. Automatic mechanisms are then developed to utilize the computable em-beddings to effectively identify mistake BIM elements. The framework is validated using illustrative examples and the results show that 100% mistake elements can be identified successfully without human intervention.

关键词： Building information modeling Quantity take -off BIM information quality BIM model auditing knowledge graph embedding

来源：评论

学校读者我要写书评

暂无评论

Relation-aware collaborative autoencoder for personalized multiple facet selection

引用

knowledge-BASED SYSTEMS 2022年 246卷 1页

作者： Chantamunee, Siripinyo Wong, Kok Wai Fung, Chun Che Murdoch Univ Discipline Informat Technol Perth Australia Walailak Univ Sch Engn & Technol Nakhon Si Thammarat Thailand Walailak Univ Informat Innovat Ctr Excellence Nakhon Si Thammarat Thailand

Collaborative-based personalization has been one of the most successful techniques used in building personalization for recommender systems and facet selection. The technique predicts users' interests based on the preferences of similar people or items. The prediction is usually made on one single group of users or items/facets. However, multiple facet selection creates a different challenge where the prediction needs to be based on the similarity among different groups of users and facets. In conventional collaborative approach, user-facet representation is created from the concatenation of user preferences on each facet. This creates a spared representation which affects the accuracy of the personalized model. It is essential to develop a more suitable representation that effectively represents the collaborative preferences given across multiple facets and a predictive model to estimate the possible preferences across those groups. Multiple facets appear to be correlated to each other and this can be useful for associating the existing preferences. None of the previous works has addressed the issue due to the association of facet relationships. Hence, this paper aims to examine the effectiveness of a new approach that utilizes multiple-facet relationships to associate the collaborative interests across different facets. This study proposes a new collaborative-based personalization model for multiple facet selection, called Relation-aware Collaborative Autoencoder (RCAE) Model. A new embedding methodology was introduced for incorporating multiple facet relationships into user-facet interaction. Evaluations based on four real-world datasets demonstrated that the proposed model utilizing facet relationships has achieved significant improvement over the conventional collaborative approach. (C)& nbsp;2022 Elsevier B.V. All rights reserved.

关键词： Multiple facets Personalized facet selection Collaborative-based personalization Autoencoder Deep neural network knowledge graph embedding

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：