检索结果-内蒙古大学图书馆

IEEE International Conference on Smart Computing (SMARTCOMP)

作者： Li, Jingyi Chen, Qi Wang, Wei Wu, Fangyu Xian Jiaotong Liverpool Univ Sch AI & Adv Comp Suzhou Peoples R China Xian Jiaotong Liverpool Univ Dept Comp Suzhou Peoples R China Xian Jiaotong Liverpool Univ Dept Intelligent Sci Suzhou Peoples R China

ISBN: (纸本)9798350322811

Social media plays an irreplaceable role in shaping the way information is created shared and consumed. While it provides access to a vast amount of data, extracting and analyzing useful insights from complex and dynamic social media data can be challenging. Deep learning models have shown promise in social media analysis tasks, but such models require a massive amount of labelled data which is usually unavailable in real-world settings. Additionally, these models lack common-sense knowledge which can limit their ability to generate comprehensive results. To address these challenges, we propose a knowledge-embedded prompt learning model for zero-shot social media text classification. Our experimental results on four social media datasets demonstrate that our proposed approach outperforms other well-known baselines.

关键词： Zero-shot text classification prompt learning knowledge graph embedding social media data analysis

来源：评论

学校读者我要写书评

暂无评论

embedding knowledge graphs in Function Spaces 24

Embedding Knowledge Graphs in Function Spaces

引用

33rd ACM International Conference on Information and knowledge Management (CIKM)

作者： Teyou, Louis Mozart Kamdem Demir, Caglar Ngomo, Axel-Cyrille Ngonga Paderborn Univ Elect Informat & Math Paderborn North Rhine Wes Germany

ISBN: (纸本)9798400704369

We introduce a novel embedding method diverging from conventional approaches by operating within function spaces of finite dimension rather than finite vector space, thus departing significantly from standard knowledge graph embedding techniques. Initially employing polynomial functions to compute embeddings, we progress to more intricate representations using neural networks with varying layer complexities. We argue that employing functions for embedding computation enhances expressiveness and allows for more degrees of freedom, enabling operations such as composition, derivatives and primitive of entities representation. Additionally, we meticulously outline the step-by-step construction of our approach and provide code for reproducibility, thereby facilitating further exploration and application in the field.

关键词： Function space knowledge graph knowledge graph embedding Polynomial function Neural Networks

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

Fast Hubness-Reduced Nearest Neighbor Search for Entity Alignment in knowledge graphs

引用

SN Computer Science 2022年第6期3卷 501页

作者： Obraczka, Daniel Rahm, Erhard ScaDS.AI/Database Group Leipzig University Leipzig Germany

The flexibility of knowledge graphs to represent heterogeneous entities and relations of many types is challenging for conventional data integration frameworks. In order to address this challenge the use of knowledge graph embeddings (KGEs) to encode entities from different data sources into a common lower-dimensional embedding space has been a highly active research field. It was recently discovered however that KGEs suffer from the so-called hubness phenomenon. If a dataset suffers from hubness some entities become hubs, that dominate the nearest neighbor search results of the other entities. Since nearest neighbor search is an integral step in the entity alignment procedure when using KGEs, hubness is detrimental to the alignment quality. We investigate a variety of hubness reduction techniques and (approximate) nearest neighbor libraries to show we can perform hubness-reduced nearest neighbor search at practically no cost w.r.t speed, while reaping a significant improvement in quality. We ensure the statistical significance of our results with a Bayesian analysis. For practical use and future research we provide the open-source python library kiez at https://***/dobraczka/kiez. © 2022, The Author(s).

关键词： Entity alignment Hubness reduction knowledge graph embedding Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

Can Ensemble Calibrated Learning Enhance Link Prediction? A Study on Commonsense knowledge 15th

Can Ensemble Calibrated Learning Enhance Link Prediction? A ...

引用

15th Asian Conference on Intelligent Information and Database Systems (ACIIDS)

作者： Racharak, Teeradaj Jearanaiwongkul, Watanee Thwe, Khine Myat Japan Adv Inst Sci & Technol Sch Informat Sci Nomi Japan Asian Inst Technol Khlong Luang Thailand

ISBN: (纸本)9789819958368;9789819958375

Numerous prior works have shown how we can use knowledge graph embedding (KGE) models for ranking unseen facts that are likely to be true. Though these KGE models have been shown to make good performance on the ranking task with standard benchmark datasets, in practice only a subset of the top-k ranked list is indeed correct. This is due to the fact that most knowledge graphs are built under the open world assumption, while state-of-the-art KGE exploit the closed world assumption to build negative samples for training. In this paper, we show to address this problem by ensembling calibrated learning, following the principle that multiple calibrated models can make a stronger one. In experiments on the ConceptNet of commonsense knowledge base, we show significant improvement over each individual baseline model. This suggests that ensembling calibrated learning is a promising technique to improve link prediction with KGEs.

关键词： Link prediction knowledge graph embedding Ensemble learning Commonsense knowledge base ConceptNet

来源：评论

学校读者我要写书评

暂无评论

Capturing Semantic and Syntactic Information for Link Prediction in knowledge graphs 18th

Capturing Semantic and Syntactic Information for Link Predic...

引用

18th International Semantic Web Conference (ISWC)

作者： Wang, Changjian Yan, Minghui Yi, Chuanrun Sha, Ying Chinese Acad Sci Inst Informat Engn Beijing Peoples R China Univ Chinese Acad Sci Sch Cyber Secur Beijing Peoples R China Huazhong Agr Univ Coll Informat Wuhan Peoples R China

ISBN: (纸本)9783030307936;9783030307929

Link prediction has recently been a major focus of knowledge graphs (KGs). It aims at predicting missing links between entities to complement KGs. Most previous works only consider the triples, but the triples provide less information than the paths. Although some works consider the semantic information (i.e. similar entities get similar representations) of the paths using theWord2Vec models, they ignore the syntactic information (i.e. the order of entities and relations) of the paths. In this paper, we propose RW-LMLM, a novel approach for link prediction. RW-LMLM consists of a random walk algorithm for KG (RW) and a language model-based link prediction model (LMLM). The paths generated by RW are viewed as pseudo-sentences for LMLM training. RW-LMLM can capture the semantic and syntactic information in KGs by considering entities, relations, and order information of the paths. Experimental results show that our method outperforms several state-of-the-art models on benchmark datasets. Further analysis shows that our model is highly parameter efficient.

关键词： knowledge graph embedding Link prediction Random walk Language model

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

knowledge-enhanced Spherical Representation Learning for Text Classification

Knowledge-enhanced Spherical Representation Learning for Tex...

引用

SIAM International Conference on Data Mining (SDM)

作者： Ennajari, Hafsa Bouguila, Nizar Bentahar, Jamal Concordia Univ Concordia Inst Informat Syst Engn CIISE Montreal PQ H3G 1M8 Canada

ISBN: (纸本)9781611977172

We introduce knowledge-enhanced Spherical Representation Learning (K-SRL), a generative probabilistic model of text documents that combines word embeddings and knowledge graph embeddings to effectively encode the semantic information of text and the related background knowledge into a low-dimensional representation. More specifically, the proposed model represents each text document as a combination of both words and entities linked to an external large knowledge graph and models them as points on the unit hypersphere using the von Mises-Fisher distribution. Furthermore, we develop an efficient variational Bayesian inference algorithm to learn unsupervised text embeddings in the spherical space. Experimental results on multiple benchmark datasets demonstrate that our model outperforms existing probabilistic models on common text classification tasks, including text categorization and sentiment analysis.

关键词： Representation learning von Mises-Fisher knowledge graph embedding Bayesian inference

来源：评论

学校读者我要写书评

暂无评论

AR-BERT: Aspect-relation enhanced Aspect-level Sentiment Classification with Multi-modal Explanations 22

AR-BERT: Aspect-relation enhanced Aspect-level Sentiment Cla...

引用

31st ACM Web Conference (WWW)

作者： Islam, Sk Mainul Bhattacharya, Sourangshu IIT Kharagpur Kharagpur W Bengal India

ISBN: (纸本)9781450390965

Aspect level sentiment classification (ALSC) is a difficult problem with state-of-the-art models showing less than 80% macro-F1 score on benchmark datasets. Existing models do not incorporate information on aspect-aspect relations in knowledge graphs (KGs), e.g. DBpedia. Two main challenges stem from inaccurate disambiguation of aspects to KG entities, and the inability to learn aspect representations from the large KGs in joint training with ALSC models. We propose AR-BERT, a novel two-level global-local entity embedding scheme that allows efficient joint training of KG-based aspect embeddings and ALSC models. A novel incorrect disambiguation detection technique addresses the problem of inaccuracy in aspect disambiguation. We also introduce the problem of determining mode significance in multi-modal explanation generation, and propose a two step solution. The proposed methods show a consistent improvement of 2.5 - 4.1 percentage points, over the recent BERT-based baselines on benchmark datasets.

关键词： Sentiment Analysis knowledge graph embedding Explainable Deep Learning

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：