1. CurEx – A System for Extracting, Curating, and Exploring Domain-Specific Knowledge Graphs from Text [CurEx, CIKM 2018]
2. Mining Structures of Factual Knowledge from Text: An Effort-Light Approach [PhD Thesis of Prof Xiang Ren]
3. DeepDive: Incremental Knowledge Base Construction Using DeepDive [VLDB 2015] {Paper} {Slides}{Project link}

• Distant Supervision; Build a fator graph containing both relation phrases and features.

1. Knowledge Vault: A Web-Scale Approach to Probabilistic Knowledge Fusion [Knowledge Vault, KDD 2014]
2. ClusType: Effective Entity Recognition and Typing by Relation Phrase-Based Clustering [ClusType, KDD2015] (Also Relation Clustering) croase-grained entity typing
3. Label Noise Reduction in Entity Typingby Heterogeneous Partial-Label Embedding [PLE, KDD 2016] fine-grained entity typing
4. AFET: Automatic Fine-Grained Entity Typing byHierarchical Partial-Label Embedding [AFET, EMNLP 2016] fine-grained entity typing
5. A survey of named entity recoginition and classification {Paper}
6. No Noun Phrase Left Behind: Detecting and Typing Unlinkable Entities [EMNLP-CoNLL 2012]{Paper}

Tutorial:

1. A SURVEY ON RELATION EXTRACTION (CMU) {Slides}
2. Relation Extraction: CSE 517: Natural Language Processing {Slides}
3. Relation Extraction II: CSE 517: Natural Language Processing {Slides}

Papers:

1. CoType: Joint Extraction of Typed Entities and Relations with Knowledge Bases [CoType, WWW2017] https://blog.csdn.net/hqc888688/article/details/73559365
2. [g]Knowledge-Based Weak Supervision for Information Extraction of Overlapping Relations {Code}{Slides}

• Recently, researchers have developed multi- instance learning algorithms to combat the noisy training data that can come from heuristic labeling, but their models assume relations are disjoint . for example they cannot extract the pair Founded(Jobs, Apple) and CEO-of(Jobs, Apple). This paper presents a novel approach for multi-instance learning with overlapping relations that combines a sentence-level extraction model with a simple, corpus-level component for aggregating the individual facts.

3. [g]Modeling missing data in distant supervision for information extraction [ACL2013] missing data problem(?)
4. Neural Relation Extraction with Selective Attention over Instances [ACL 2016] {Paper}{Code}{Blog}

• Fix the problem of distant supervised relation extraction
• Employs CNN to embed the semantics of sentences, then builds sentence-level attention over multi- ple instances, which is expected to dynamically reduce the weights of those noisy instances (major contribution). Notes in group meeting.

5. Multi-instance Multi-label Learning for Relation Extraction [EMMLP-CoNLL 2012]{Paper}

Notes:

1. Candiate Entity Ranking: https://www.jianshu.com/p/90e2c7a5c9f5
2. http://nlpprogress.com/english/entity_linking.html

Papers:

1. Entity Linking wuth a Knowledge Base: Issues, Techniques, and Solutions (Survey)
2. Robust Disambihguation of Named Entities in Text [EMNLP 2011]
3. Liege: Link Entities in Web Lists with Knowledge Base [KDD 2012]
4. Entity Lnking for Tweets [ACL 2013]
5. Collective Annotation of Wikipedia Entities in Webb Text [KDD 2009]
6. Local and Global Algorithms for Disambiguation to Wikipedia [ACL 2011]

Sides, Tutorials and Surveys

1. Brief Introduction and Review of Open Information Extraction System {Slides}
2. A Survey on Open Information Extraction {Paper}
3. Open Information Extraction on Scientific Text: An Evaluation {Paper}
4. https://github.com/gkiril/oie-resources

OpenIE Tools

1. Open Information Extraction from the Web [TextRunner, IJCAI 2007]

• Incoherent Extractions
• Uninformative Extractions

2. MinIE: Minimizing Facts in Open Information Extraction [MinIE, EMNLP 2017] Code (java)

• Represent information about polarity, modality, attribution and quantities with semantic annotations (instead of actual extraction)
• idetify and remove parts that are considered over specific

3. Facts that Matter [SALIE, EMNLP 2018] {Code}

• Extract salient facts, which fulfill two requirements: (1) relevance and (2) diversity

4. Identifying Relations for Open Information Extraction [ReVerb, EMNLP 2011] {Paper}{Code}{Homepage}

• Use syntactic constraints to specify relation phrases (3 simple patterns). Find longest phrase matching one of the syntactic constraints.
• Find nearest noun-phrases to the left and right of relation phrase. - Not a relative pronoun or WHO-adverb or an existential there.
• To avoid "overspecified" relation phrases, a relation phrase must have many distinct args in a large corpus

5. ClausIE: Clause-Based Open Information Extraction [ClausIE, WWW 2013] {Paper}{Code (Python)}{Code (Java)}

• Map the dependency relations of an input senetnce to clause constituents.
• A set of coherent clauses presenting a simple linguistic structure is derived from the input

OpenIE Triple Clustering

1. Query-Driven On-The-Fly Knowledge Base Construction [QKBfly, VLDB2017] relation
2. CESI: Canonicalizing Open Knowledge Bases using Embeddings and Side Information [CESI, WWW2018] Code triple
3. Canonicalizing Open Knowledge Bases [CIKM 2014] triple
4. Towards Practical Open Knowledge Base Canonicalization [FAC, CIKM 2018] triple
5. Identifying Relations for Open Information Extraction [ReVerb, EMNLP 2011] {Paper}{Code}{Homepage} relation

• Mophological Normalization

6. Open Information Extraction to KBP Relations in 3 Hours [TAC. 2013] {Paper}

• Main idea: relation phrases mapping to KB otology
• Manually define a set of rules for each relation, to conduct the mapping
• The motivation and error analysis are well written.

7. ClusType: Effective Entity Recognition and Typing by Relation Phrase-Based Clustering [ClusType, KDD2015]

• Relation Clustering: Two relation phrases tend to have similar cluster membershipd, if they have similar (1) strings; (2) context words; and (3) left and right argument type indicators

8. Unsupervised Methods for Determining Object and Relation Synonyms on the Web [Resolover, JAIR 2009] relation
9. Relation Extraction with Matrix Fatorization and Universal Schemes [NAACL-HLT 2013] {Paper}

• Close to relation clustering
• Create a universal scheme by unioning surface form predicates from Open IE and relations in the schemas of pre-existing databbases.

Relation Phrases Clustering (finding synonymous phrases and hypernyms)

1. HARPY: Hypernyms and Alignment of Relational Paraphrases [HAPPY, COLING 2014] {Paper}{Data}
2. POLY: Mining Relational Paraphrases from Multilingual Sentences [POLY, EMNLP 2016] {Paper}{Data}

• Make use of another language

3. RELLY: Inferring Hypernym Relationships Between Relational Phrases [REELY, EMNLP 2015] {Paper}{Data}
4. PATTY: A Taxonomy of Relational Patterns with Semantic Types [PATTY, EMNLP 2012] {Paper}{Data}
5. Discovering and Exploring Relations on the Web [PATTY demo, VLDB 2012] {Paper}
6. [g]Ensemble Semantics for Large-Scale Unsupervised Relation Extraction [WEBRE, EMNLP-CoNELL 2012] relation
7. [g]Relation Schema Induction using Tensor Factorization with Side Information [SICTF, EMNLP 2016] relation schema induction (for building domain-specific kb from unstructured text) Code: https://github.com/malllabiisc/sictf
8. [g]Constrained Information-Theoretic Tripartite Graph Clustering to Identify Semantically Similar Relations [IJCAI 2015]

Relation Linking

1. Old is Gold: Linguistic Driven Approach for Entity and Relation Linking of Short Text [FALCON, NAACL 2019] {Paper} {Code}{Demo}{Notes}
2. EARL: Joint Entity and Relation Linking for Question Answering [EARL, ISWC 2018] {Paper} {Code}

Others

1. Intergring Local Context and Global Cohesiveness for Open Information Extraction [ReMine, WSDM 2019]

• Solving a joint optimization problem to unify (1) segmenting entity/relation phrases in individual sentences based on local context; and (2) measuring the quality of tuples extracted from individual sentences with a translating-based objective.

1. DeepWalk: Online Learning of Social Representations [DeepWalk, KDD 2014] [Code] (https://github.com/phanein/deepwalk Slides: https://www.slideshare.net/bperz/14-kdddeep-walk-2)

• Use a sentence embedding model

2. [g]DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning [DeepPath, EMNLP 2017] [Code](https://github.com/xwhan/DeepPath Notes: https://zhuanlan.zhihu.com/p/33536026)
3. [g]Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs [Know-Evolve, ICML 2017]{Paper}{Code (C++)}
4. [g]Reading and Reasoning with Knowledge Graphs [PhD Thesis of Matthew Gardner] {Thesis}

• Reasoning, Relation Extraction, Modeling Lexical Semantics

5. EventKG: A Multilingual Event-Centric Temporal Knowledge Graph

• Has time and location info
• A system that integrates knowledge from different existing KBs

6. Knowledge Graph Embedding: A Survey of Approaches and Applications {Paper}
7. Multilingual Knowledge Graph Embedding for Cross-lingual Knowledge Alignment. {Slides}

1. [g]Dynamic Word Embeddings {Paper}
2. [g]DYREP: LEARNING REPRESENTATIONS OVER DYNAMIC GRAPHS [ICLR 2019] {Paper}
3. [g]Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs [Know-Evolve, ICML 2017]{Paper}{Code (C++)}
4. [g] Continuous-Time Dynamic Network Embeddings [WWW 2018] {Paper}

Survey:

1. Knowledge Graph Refinement:A Survey of Approaches and Evaluation Methods

Knowledge Base Completion:

1. Knowledge base completion via search-based question answering [WWW 2014]{Paper}
2. Knowledge base completion via coupled path ranking [ACL 2016]{Paper}

Knowledge Base Population:

1. Overview: https://nlp.stanford.edu/projects/kbp/
2. Slides of Summary: https://pdfs.semanticscholar.org/8193/1b57a1760a4fc9e8b42065bebcab4cbf164e.pdf

1. A Fresh Look on Knowledge Bases Distilling Named [CIKM 2014]

• Event KB. Each news article is regarded as a event. Build the semantic similarity relations and the tmporal relations between evernts.

2. CERES: Distantly Supervised Relation Extractionfrom the Semi-Structured Web [CERES, VLDB 2018]
3. When Open Information Extraction Meets the Semi-Structured Web [OpenCERES, NAACL 2019]
4. How to Keep a Knowledge Base Synchronized with Its Encyclopedia Source [IJCAI 2017] {Notes}

1. https://kgtutorial.github.io An introduction to knowledge graph and knowledge extraction from unstructured text.
2. https://github.com/impillar/knowledge_graph/blob/master/README.md
3. https://github.com/BrambleXu/knowledge-graph-learning
4. https://github.com/Pelhans/Z_knowledge_graph
5. https://zhuanlan.zhihu.com/p/44904796
6. Information Extraction by Niranjan Balasubramanian {Slides in my Mac}

1. Probabilistic Graphical Models: Lagrangian Relaxation Algorithms for Natural Language Processing {Slides}
2. Introduction to Conditional Random Fields {Blog}
3. Network Community Detection: A Review and Visual Survey {Paper}

• Section 2.3. Community Detection Techniques

4. Fast unfolding of communities in large networks {Paper}

• A discussion of the Louvain method: https://www.quora.com/Is-there-a-simple-explanation-of-the-Louvain-Method-of-community-detection, wiki of the Louvein Modularity: https://en.wikipedia.org/wiki/Louvain_Modularity
• How do they design the function Q: Finding and evaluating community structure in networks {Paper}

5. A compendium of NP optimization problems http://www.nada.kth.se/~viggo/wwwcompendium/
6. Notes about LSH: https://blog.csdn.net/yc461515457/article/details/48845775
7. Survey about Min Hash Sketch: http://www.cohenwang.com/edith/Surveys/minhash.pdf
8. MinHash Tutorial with Python Code: https://mccormickml.com/2015/06/12/minhash-tutorial-with-python-code/ https://github.com/chrisjmccormick/MinHash
9. GNN: https://github.com/thunlp/GNNPapers

1. Wikidata Integrator
2. Stanford KBP
3. DBpeida Spotlight
4. OpenTapioca {Link}

1. spaCy {[Link](https://spacy.io/api/annotation#section-named-entities https://towardsdatascience.com/named-entity-recognition-with-nltk-and-spacy-8c4a7d88e7da)}
2. NLTK
3. DBpedia Spotlight {Link}

1. BOOKNLP https://github.com/dbamman/book-nlp (a natural language processing pipeline that scales to books and other long documents (in English))

1. From Freebase to Wikidata: The Great Migration {Paper and useful links}
2. SPASQL tutorial {Link}
3. Installing and running ElasticSearch {Link}
4. Open KG on COVID-19 [Link]