- Constructing Domain-specific Knowledge Graphs (AAAI 2018) [Tutorial]
- Domain-specific Knowledge Graphs: A survey (2020) [Paper]
General Domain-Specific KB Construction and Refinement
- Towards the Completion of a Domain-Specific Knowledge Base with Emerging Query Terms [PDF] (ICDE 2019) 🌟
- Demonstrating Spindra: A Geographic Knowledge Graph Management System [PDF, demo] (ICDE 2019) 🌟
- Domain Specific Knowledge Graphs as a Service to the Public (KDD 2020, Applied Data Science Track) 🌟
- Probase: A Probabilistic Taxonomy for Text Understanding (SIGMOD 2012)🌟
ProBase : Microsoft Conceptual Graph
- iterative learning algorithm for extraction and taxonomy construction algorithm
- a probabilistic framework
- largest general-purpose taxonomy fully automatically constructed
- Semantic Enrichment of Data for AI Applications (DEEM 2021)
LLM for Domain-Specific KG Constrcution 🔥🔥🔥
- BEAR: Revolutionizing Service Domain Knowledge Graph Construction with LLM (ICSOC 2023) [Paper]
Domain Specific NER
- Learning Named Entity Tagger using Domain-Specific Dictionary [Paper] [Notes]
- A Hybrid Generative/Discriminative Model for Rapid Prototyping of Domain-Specific Named Entity Recognition [Paper]
- CHEMNER: Fine-Grained Chemistry Named Entity Recognition with Ontology-Guided Distant Supervision (EMNLP 2021) [Paper]
Domain Specific EL
- SHINE+: A General Framework for Domain-Specific Entity Linking with Heterogeneous Information Networks (TKDE 2018) 🌟
- A Semantic Approach for Entity Linking by Diverse Knowledge Integration incorporating Role-Based Chunking ((ICCIDS 2019)
- Towards Linking Camouflaged Descriptions to Implicit Products in E-commerce (SIGIR 2020) [Paper]
- Medical Entity Disambiguation using Graph Neural Networks (SIGMOD 2021) 🌟
Taxonomies of Domain Specific KBs
- TiFi: Taxonomy Induction for Fictional Domains? (WWW 2019)
Keynotes and Tutorials
- Amazon Product Graph [Slides]
- Self-Driving Product Understanding for Thousands of Categories (By Luna Dong, Keynote at Knowledge Graphs and E-commerce Workshop, San Diego, CA, August 2020) [Slides]
- Building a Broad Knowledge Graph for Products (By Luna Dong, Keynote at IEEE International Conference on Data Engineering (ICDE), Macau, China, April 2019) [Slides]
Research Papers
- AutoKnow: Self-Driving Knowledge Collection for Products of Thousands of Types (KDD 2020, Applied Data Science Track) [Paper]🌟
- GoodsKG - a Product Knowledge Graph Project [GitHub]
- AliCoCo: Alibaba E-commerce Cognitive Concept Net (SIGMOD 2020 Industry Track) [Paper] [Github]🌟
- Product Knowledge Graph Embedding for E-commerce (WSDM 2020) [Paper]🌟
- Towards Knowledge-Based Personalized Product Description Generation in E-commerce [Paper, applied science track] (KDD 2019) 🌟
- TXtract: Taxonomy-aware knowledge extraction for thousands of product categories (ACL 2020)
- Automatic validation of textual attribute values in eCommerce Catalog by learning with limited labeled data (KDD 2020) 🌟
- Octet: Online catalog taxonomy enrichment with self-supervision (KDD 2020) 🌟
- OpenTag: Open attribute value extraction from product profiles (KDD 2018) 🌟
- DEXTER: Large-scale discovery and extraction of product specifications on the Web (VLDB 2016) 🌟
- P-Companion: A principled framework for diversified complementary product recommendation (CIKM 2020)
- J-Recs: Principled and scalable recommendation justification (ICDM 2020)
- PAM: Understanding Product Images in Cross Product Category Attribute Extraction (KDD 2021) [Paper]
- AliCoCo2: Commonsense Knowledge Extraction, Representation and Application in E-commerce (KDD 2021) 🌟
- AliCG : Alibaba Conceptual Graph for Semantic Search (KDD 2021) 🌟
- AliMe KG : Alibaba domain knowledge graph in E-commerce (CIKM 2020)
- Embedding-based Product Retrieval in Taobao Search (KDD 2021) [Paper] 🌟
- Product Knowledge Graph Embedding for E-commerce (WSDM 2020) [Paper]
- Weakly-Supervised Opinion Summarization by Leveraging External Information (AAAI 2020)
- PGE: Robust Product Graph Embedding Learning for Error Detection (arxiv 2022, Luna's team) [Paper]
Datasets
- Web Data Commons - Gold Standard for Product Matching and Product Feature Extraction [Link]
Note: Medical entity linking is also referred to as medical concept normalization (MCN)
Research Papers
- MedPath: Augmenting Health Risk Prediction via Medical Knowledge Paths (WWW 2021)
- Personalized KG to provided personalized prediction and explicit reasoning.
- The major idea is borrowed from MHGRN (multi-hop graph): Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering (EMNLP 2020) [Paper] [Notes in Chinese]
- Medical Entity Disambiguation using Graph Neural Networks (SIGMOD 2021) 🌟
- This work introduces
ED-GNN
based on three representative GNNs (GraphSAGE, R-GCN, and MAGNN) for Medical ED.- There are two optimization techniques: (1) a novel strategy to represent entities mentioned in text snippets as a query graph; (2) an effective negative sampling strategy.
- Property Graph Schema Optimization for Domain-Specific Knowledge Graphs (ICDE 2021) 🌟
- MEDTO: Medical Data to Ontology Matching Using Hybrid Graph Neural Networks (KDD 2021) 🌟
- DETERRENT: Knowledge Guided Graph Attention Network for Detecting Healthcare Misinformation (KDD 2020) 🌟 [Paper] [GitHub]
Healthcare Misinformation Detection
- A novel problem of explainable healthcare misinformation detection (from the web) by leveraging medical knowledge graph to better capture the high-order relations between entities.
- RGCN (with attention) for KG reasoning + text encoer of articles = learn the representation for each earticle, then formulate a classification problem to distinguish if a news is fake.
- The support KG: KnowLife: a versatile approach for constructing a large knowledge graph for biomedical sciences [Paper] [Website]
- Similar basic code (text+GRU+RGCN): Learning to Update Knowledge Graphs by Reading News (EMNLP 2019) [GitHub]
- CHEMNER: Fine-Grained Chemistry Named Entity Recognition with Ontology-Guided Distant Supervision (EMNLP 2021) [Paper]
- Kformer: Knowledge Injection in Transformer Feed-Forward Layers [Arxiv 2022]
- There is a medical QA task in the experiment based on a [Medical KB].
- Taiyi: A Bilingual Fine-Tuned Large Language Model for Diverse Biomedical Tasks (Arxiv, Nov 2023) [Paper] 🔥
- Datasets: a comprehensive collection of 140 existing biomedical text mining datasets (38 Chinese datasets and 102 English datasets)
- Tasks: named entity recognition, relation extraction, text classification, question answering tasks
- LLMs Accelerate Annotation for Medical Information Extraction (PMLR 2023) [Paper] 🔥
Datasets
- PubMed
- MDX [Link]
- MIMIC-III [Reference]
- Bio CDR [Reference]
- NCBI [Reference], NCBID [Reference]
- ShARe [Reference]
- BioCreative [Reference]
- Summary from NormCo [Github]
- Datasets provided by [MedType]: [WikiMed] and [PubMedDS]
- Unified Medical Language System (UMLS): 4.2 million biomedical concepts, with 127 types
- There is a UMLS Semantic Network for concept mapping to semantic types?
- Precision Medicine Knowledge Graph (PrimeKG) presents a holistic view of diseases. PrimeKG integrates 20 high-quality biomedical resources to describe 17,080 diseases with 4,050,249 relationships representing ten major biological scales.
Useful tools (mainly for NER and EL to preprecess the data)
- Resources Collection: AwesomeBioIE [GitHub]
BioBERT for NER (and RE)
BioBERT: a pre-trained biomedical language representation model for biomedical text mining [Paper] [GitHub]DeepMatcher for EM
: Deep Learning for Entity Matching: A Design Space Exploration (SIGMOD 2018) [PDF] [Code and Data] 🌟NCEL for EL
: Neural Collective Entity Linking (COLING 2018) [Paper] [Github]SciSpacy (as neural med-linker)
: SciSpaCy: Fast and Robust Models for Biomedical Natural Language Processing (arxiv 2019) [GitHub]cTAKES for medical entity linker
(map named entities to UMLS concepts) [Reference]Quick-UMLS for medical entity linker
MetaMap for medical entity linker
(map biomedical mentions in text to UMLS concepts) [Tool]
MetaMapLite
: reimplements baisc MetaMap with an additional emphasis on real-time processing and competitive performance [Tool]
- "After installing medaCy and medaCy's clinical model..." I come across the same issue as #210 and #209, will figure out later.
- An Advanced Review on Text Mining in Medicine [Website]
People
Materials
- The Construction and Applications of Medical KGs (in Chinese, 医疗领域图谱的构建与应用) [Link]
Survey and Intersting Discussion
- Financial Risk Analysis for SMEs with Graph-based Supply Chain Mining (IJCAI 2020, Special Track on AI in FinTech) [Paper]
- The SME graph as well as the labeled data for supply chain mining are from Alipay.
- 综述 | GNN金融风控领域业界进展调研 [Link]
Datasets
- Fannie Mae Single-Family Loan Performance Data [Link 1] [Link 2]
- Data Set and Evaluation of Automated Construction of Financial Knowledge Graph [Link]
- 企业知识图谱 [Link]
- 金融时序超图(Finanical Temporal Hypergraph Ontology,FTHO) [Link]
- 基金知识图谱 [Link]
- 其他中文金融相关知识图谱数据集 [Link]
Research Papers
- Personalized Knowledge Graph Summarization: From the Cloud to Your Pocket (ICDM 2019 Best Paper) [Paper]
- Knapsack, submodula objective function, (1 − {1}{e})-approximation algorithm
- What is Normal, What is Strange, and What is Missing in a Knowledge Graph: Unified Characterization via Inductive Summarization (WWW 2020) [Paper]
Research Papers
- Searching News Articles Using an Event Knowledge Graph Leveraged by Wikidata (WWW 2019) [Paper]
- NewsLink: Empowering Intuitive News Search with Knowledge Graphs (ICDE 2021)
- ASER: A Large-scale Eventuality Knowledge Graph (WWW 2020) [Paper] [Code]
Research Papers
- Knowledge-aware Assessment of Severity of Suicide Risk for Early Intervention (WWW 2019)
- FoodKG: A Semantics-Driven Knowledge Graph for Food Recommendation (ISWC 2019) [Github]
- Modern Natural Language Processing Techniques for Scientific Web Mining: Tasks, Data, and Tools (WWW 2022 tutorial)
- UUKG: Unified Urban Knowledge Graph Dataset for Urban Spatiotemporal Prediction (NeurIPS 2023, Datasets and Benchmarks Track) [Paper]