论文集 | 精选133篇知识图谱论文

• 2021 年 11 月 8 日
• AI
• 知识图谱

从广义上来说，知识图谱是一个包括知识表示、知识构建、知识维护以及知识应用的完整生态系统，它不仅包含特定领域中的知识定义和实例数据，还包含了支撑描述、构建、储存、管理和应用知识所需的配套标准、技术和工具。

论文由网盘发送……但链接老失效，可以联系深蓝学院-子书（v：shenlan-zishu），备注【精选】，才会通过好友哦！

//fss.mpay8.cn/article/cngMdbl4mi

​知识图谱是人工智能领域的重要分支，也是机器具有认知能力的基石，随着知识图谱技术研究与应用的深化，该方向吸引了来自工业界和学术界的广泛关注，相关技术已经在金融证券、生物医疗、图书情报、电商、农业、政府、电信和出版等领域得到较为广泛的应用。

比如在金融证券领域，利用图计算的方法构建科学、严谨的企业风险评估体系，有效规避潜在的经营风险与资金风险。

​

并且通过不一致性验证可以判断借款人的欺诈风险，也就是我们常说的反欺诈。

​

当前知识图谱相关的顶会论文也越来越多，我们特地精选值得细读的100篇（2019-2021），包括知识表示学习、知识构建与信息抽取、知识语义计算与理解、知识增强与应用等四个方面。

知识表示学习

• Dual Quaternion Knowledge Graph Embeddings
• ChronoR: Rotation Based Temporal Knowledge Graph Embedding
• PASSLEAF: A Pool-Based Semi-Supervised Learning Framework for Uncertain Knowledge Graph Embedding
• Topology-Aware Correlations between Relations for Inductive Link Prediction in Knowledge Graphs
• Learning from History: Modeling Temporal Knowledge Graphs with Sequential CopyGeneration Networks
• Neural Latent Space Model for Dynamic Networks and Temporal Knowledge Graphs
• 5 Knowledge Graph Embeddings with Projective Transformations

知识构建与信息抽取

• Type-Augmented Relation Prediction in Knowledge Graphs
• Dynamic Hybrid Relation Exploration Network for Cross-Domain Context-Dependent Semantic Parsing
• FL-MSRE: A Few-Shot Learning Based Approach to Multimodal Social Relation Extraction
• Multi-View Inference for Relation Extraction with Uncertain Knowledge
• Multi-Modal Graph Fusion for Named Entity Recognition with Targeted Visual Guidance
• GDPNet: Refining Latent Multi-View Graph for Relation Extraction
• Relation-Aware Neighborhood Matching Model for Entity Alignment
• Read, Retrospect, Select: An MRC Framework to Short Text Entity Linking
• KEML: A Knowledge-Enriched Meta-Learning Framework for Lexical Relation Classification
• Progressive Multi-Task Learning with Controlled information Flow for Joint Entity and Relation Extraction
• Curriculum-Meta Learning for Order-Robust Continual Relation Extraction
• Document-Level Relation Extraction with Reconstruction
• CrossNER: Evaluating Cross-Domain Named Entity Recognition
• A Bidirectional Multi-Paragraph Reading Model for Zero-Shot Entity Linking
• A Supervised Multi-Head Self-Attention Network for Nested Named Entity Recognition
• Knowledge Refinery: Learning from Decoupled Label
• Generalized Relation Learning with Semantic Correlation Awareness for Link Prediction
• Nested Named Entity Recognition with Partially-Observed TreeCRFs
• Improving the Efficiency and Effectiveness for Bert-Based Entity Resolution
• Continual Learning for Named Entity Recognition
• A Unified Multi-Task Learning Framework for Joint Extraction of Entities and Relations
• A Lightweight Neural Model for Biomedical Entity Linking
• Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling
• Entity Structure Within and Throughout: Modeling Mention Dependencies for DocumentLevel Relation Extraction
• DDRel: A New Dataset for Interpersonal Relation Classification in Dyadic Dialogues
• (Comet-) Atomic 2020: On Symbolic and Neural Commonsense Knowledge Graphs
• Span-Based Event Coreference Resolution
• Knowledge-Aware Named Entity Recognition with Alleviating Heterogeneity
• Visual Pivoting for (Unsupervised) Entity Alignment
• Empower Distantly Supervised Relation Extraction with Collaborative Adversarial Training
• Clinical Temporal Relation Extraction with Probabilistic Soft Logic Regularization and Global Inference
• Denoising Distantly Supervised Named Entity Recognition via a Hypergeometric Probabilistic Model
• MTAAL: Multi-Task Adversarial Active Learning for Medical Named Entity Recognition and Normalization
• Dynamic Knowledge Graph Alignment
• GATE: Graph Attention Transformer Encoder for Cross-Lingual Relation and Event Extraction
• Few-Shot Named Entity Recognition: An Empirical Baseline Study
• Learning from Noisy Labels for Entity-Centric Information Extraction
• Data Augmentation for Cross-Domain Named Entity RecognitionFine-grained Entity Typing via Label Reasoning
• Progressive Adversarial Learning for Bootstrapping: A Case Study on Entity Set Expansion
• RockNER: A Simple Method to Create Adversarial Examples for Evaluating the Robustness of Named Entity Recognition Models
• Low-Rank Subspaces for Unsupervised Entity Linking
• Highly Parallel Autoregressive Entity Linking with Discriminative Correction
• End-to-End Entity Resolution and Question Answering Using Differentiable Knowledge
• From Alignment to Assignment: Frustratingly Simple Unsupervised Entity Alignment
• Robustness Evaluation of Entity Disambiguation Using Prior Probes: the Case of Entity Overshadowing
• Document-level Entity-based Extraction as Template Generation
• Injecting Entity Types into Entity-Guided Text Generation
• Enhanced Language Representation with Label Knowledge for Span Extraction
• Knowing False Negatives: An Adversarial Training Method for Distantly Supervised Relation Extraction
• A Partition Filter Network for Joint Entity and Relation Extraction
• A Novel Global Feature-Oriented Relational Triple Extraction Model based on Table Filling
• Modular Self-Supervision for Document-Level Relation Extraction
• Exploring Task Difficulty for Few-Shot Relation Extraction
• MapRE: An Effective Semantic Mapping Approach for Low-resource Relation Extraction
• Label Verbalization and Entailment for Effective Zero and Few-Shot Relation Extraction
• Gradient Imitation Reinforcement Learning for Low Resource Relation Extraction
• Separating Retention from Extraction in the Evaluation of End-to-end Relation Extraction
• Extracting Event Temporal Relations via Hyperbolic Geometry
• Utilizing Relative Event Time to Enhance Event-Event Temporal Relation Extraction
• Corpus-based Open-Domain Event Type Induction
• Honey or Poison? Solving the Trigger Curse in Few-shot Event Detection via Causal Intervention
• A Relation-Oriented Clustering Method for Open Relation Extraction
• Zero-Shot Information Extraction as a Unified Text-to-Triple Translation
• Entity Relation Extraction as Dependency Parsing in Visually Rich Documents
• Cost-effective End-to-end Information Extraction for Semi-structured Document Images
• Everything Is All It Takes: A Multipronged Strategy for Zero-Shot Cross-Lingual Information Extraction
• XLEnt: Mining a Large Cross-lingual Entity Dataset with Lexical-Semantic-Phonetic Word Alignment
• Uncovering Main Causalities for Long-tailed Information Extraction
• Unsupervised Keyphrase Extraction by Jointly Modeling Local and Global Context
• Back to the Basics: A Quantitative Analysis of Statistical and Graph-Based Term Weighting Schemes for Keyword Extraction
• Importance Estimation from Multiple Perspectives for Keyphrase Extraction
• DILBERT: Customized Pre-Training for Domain Adaptation with Category Shift, with an Application to Aspect Extraction
• PASTE: A Tagging-Free Decoding Framework Using Pointer Networks for Aspect Sentiment Triplet Extraction
• An Empirical Study on Leveraging Position Embeddings for Target-oriented Opinion Words Extraction

知识语义计算与理解

• Comprehension and Knowledge
• Imagine, Reason and Write: Visual Storytelling with Graph Knowledge and Relational Reasoning
• Transformer-Style Relational Reasoning with Dynamic Memory Updating for Temporal Network Modeling
• KG-BART: Knowledge Graph-Augmented Bart for Generative Commonsense Reasoning
• Communicative Message Passing for Inductive Relation Reasoning
• Neural Relational Inference with Efficient Message Passing Mechanisms
• GaussianPath: A Bayesian Multi-Hop Reasoning Framework for Knowledge Graph Reasoning
• Relation-Aware Graph Attention Model with Adaptive Self-Adversarial Training
• Making the Relation Matters: Relation of Relation Learning Network for Sentence Semantic Matching
• Randomized Generation of Adversary-Aware Fake Knowledge Graphs to Combat Intellectual Property Theft
• LET: Linguistic Knowledge Enhanced Graph Transformer for Chinese Short Text Matching
• Hierarchical Relational Inference

知识增强与应用

• Knowledge-Driven Data Construction for Zero-Shot Evaluation in Commonsense Question Answering
• Knowledge-Enhanced Hierarchical Graph Transformer Network for Multi-Behavior Recommendation
• Few-Shot Class-Incremental Learning via Relation Knowledge Distillation
• Knowledge-Driven Distractor Generation for Cloze-Style Multiple Choice Questions
• Answering Complex Queries in Knowledge Graphs with Bidirectional Sequence Encoders
• Knowledge-Guided Object Discovery with Acquired Deep Impressions
• Encoding Human Domain Knowledge to Warm Start Reinforcement Learning
• Knowledge-Enhanced Top-K Recommendation in Poincaré Ball
• ERNIE-ViL: Knowledge Enhanced Vision-Language Representations through Scene Graphs
• 6350: Unanswerable Question Correction in Question Answering over Personal Knowledge Base
• 6672: Entity Guided Question Generation with Contextual Structure and Sequence Information Capturing
• 7812: Text-Based RL Agents with Commonsense Knowledge: New Challenges, Environments and Baselines
• 7833: Knowledge-Driven Natural Language Understanding of English Text and its Applications
• Judgment Prediction via Injecting Legal Knowledge into Neural Networks
• Encoding Syntactic Knowledge in Transformer Encoder for Intent Detection and Slot Filling
• Knowledge-Aware Coupled Graph Neural Network for Social Recommendation
• Commonsense Knowledge Augmentation for Low-Resource Languages via Adversarial Learning
• Humor Knowledge Enriched Transformer for Understanding Multimodal Humor
• Infusing Multi-Source Knowledge with Heterogeneous Graph Neural Network for Emotional Conversation Generation
• Knowledge-Aware Leap-LSTM: Integrating Prior Knowledge into Leap-LSTM towards Faster Long Text Classification
• Benchmarking Knowledge-Enhanced Commonsense Question Answering via Knowledge-toText Transformation
• Dynamic Neuro-Symbolic Knowledge Graph Construction for Zero-Shot Commonsense Question Answering

分类来自于网络，如有侵权可删。