Skip to content

A collection of important open knowledge graph (OKG) construction, canonicalization and representation learning papers with implementations.

Notifications You must be signed in to change notification settings

Yang233666/Awesome-Open-Knowledge-Graphs

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

52 Commits
 
 
 
 

Repository files navigation

Awesome-Open-Knowledge-Graphs

If you like our project, please give us a star ⭐ on GitHub for the latest update.

Awesome PRs Welcome GitHub issues GitHub forks GitHub stars

A collection of important Open Knowledge Graph (OKG) resources: research papers, code, data, applications, etc. This collection is not limited to Open Knowledge Graphs but also includes their downstream applications.

We will try to make this list updated frequently. If you find any error or any missed paper, please don't hesitate to open issues or pull requests.

Table of contents

Introduction to Open Knowledge Graphs

Open Information Extraction (OIE) systems aim to extract unseen relations and their arguments from unstructured text in unsupervised manner. In its simplest form, given a natural language sentence, they extract information in the form of a triple, consisted of subject (S), relation (R) and object (O).

Suppose we have the following input sentence:

AMD, which is based in U.S., is a technology company.

An OIE system aims to make the following extractions:

("AMD"; "is based in"; "U.S.")
("AMD"; "is"; "technology company")

Papers by venues

2022

[SIGKDD' 2022] Multi-View Clustering for Open Knowledge Base Canonicalization [Paper | Code | Video]

Wei Shen, Yang Yang, Yinan Liu

2021

[SIGMOD' 2021] Joint Open Knowledge Base Canonicalization and Linking [Paper | Code | Video]

Yinan Liu, Wei Shen, Yuanfei Wang, Jianyong Wang, Zhenglu Yang, Xiaojie Yuan

[ICDE' 2021] CaSIE: Canonicalize and Informative Selection of the OpenIE system [Paper]

Hao Xin, Xueling Lin, Lei Chen

[ACL' 2021] OKGIT: Open Knowledge Graph Link Prediction with Implicit Types [Paper | Code | Video]

Chandrahas, Partha Pratim Talukdar

[EMNLP' 2021] Open Knowledge Graphs Canonicalization using Variational Autoencoders [Paper | Code | Video]

Sarthak Dash, Gaetano Rossiello, Nandana Mihindukulasooriya, Sugato Bagchi, Alfio Gliozzo

2020

[VLDB' 2020] KBPearl: A Knowledge Base Population System Supported by Joint Entity and Relation Linking [Paper | Code | Readme]

Xueling Lin, Haoyang Li, Hao Xin, Zijian Li, Lei Chen

[ACL' 2020] Can We Predict New Facts with Open Knowledge Graph Embeddings? A Benchmark for Open Link Prediction [Paper | Code | Resources | Video]

Samuel Broscheit, Kiril Gashteovski, Yanjie Wang, Rainer Gemulla

[Eval4NLP@EMNLP' 2020] On Aligning OpenIE Extractions with Knowledge Bases: A Case Study [Paper | Resources | Video | Slides]

Kiril Gashteovski, Rainer Gemulla, Bhushan Kotnis, Sven Hertling, Christian Meilicke

[WISE' 2020] MULCE: Multi-level Canonicalization with Embeddings of Open Knowledge Bases [Paper]

Tien-Hsuan Wu, Ben Kao, Zhiyong Wu, Xiyang Feng, Qianli Song, Cheng Chen

[CoRR' 2020] Canonicalizing Open Knowledge Bases with Multi-Layered Meta-Graph Neural Network [Paper]

Tianwen Jiang, Tong Zhao, Bing Qin, Ting Liu, Nitesh V. Chawla, Meng Jiang

[CoRR' 2020] Language Models are Open Knowledge Graphs [Paper]

Chenguang Wang, Xiao Liu, Dawn Song

2019

[ICDE' 2019] Canonicalization of Open Knowledge Bases with Side Information from the Source Text [Paper | Code | Dataset Description]

Xueling Lin, Lei Chen

[EMNLP' 2019].CaRe: Open Knowledge Graph Embeddings [Paper | Code]

Swapnil Gupta, Sreyash Kenkre, Partha Talukdar

[EMNLP' 2019] Collaborative Policy Learning for Open Knowledge Graph Reasoning [Paper | Code]

Cong Fu, Tong Chen, Meng Qu, Woojeong Jin, Xiang Ren

[AKBC' 2019] OPIEC: An Open Information Extraction Corpus [Paper | Data + Resources | Code (data reading) | Code (pipeline)]

Kiril Gashteovski, Sebastian Wanner, Sven Hertling, Samuel Broscheit, Rainer Gemulla

2018

[WWW' 2018] CESI: Canonicalizing Open Knowledge Bases using Embeddings and Side Information [Paper | Code]

Shikhar Vashishth, Prince Jain, Partha Talukdar

[CIKM' 2018] Towards Practical Open Knowledge Base Canonicalization [Paper]

Tien-Hsuan Wu, Zhiyong Wu, Ben Kao, Pengcheng Yin

2014

[CIKM' 2014] Canonicalizing Open Knowledge Bases [Paper]

Luis Galárraga, Geremy Heitz, Kevin Murphy, Fabian M. Suchanek

Papers by categories

Survey Papers

Evaluation

Open Knowledge Graph Canonicalization

[SIGKDD' 2022] Multi-View Clustering for Open Knowledge Base Canonicalization [Paper | Code | Video]

Wei Shen, Yang Yang, Yinan Liu

[SIGMOD' 2021] Joint Open Knowledge Base Canonicalization and Linking [Paper | Code | Video]

Yinan Liu, Wei Shen, Yuanfei Wang, Jianyong Wang, Zhenglu Yang, Xiaojie Yuan

[EMNLP' 2021] Open Knowledge Graphs Canonicalization using Variational Autoencoders [Paper | Code | Video]

Sarthak Dash, Gaetano Rossiello, Nandana Mihindukulasooriya, Sugato Bagchi, Alfio Gliozzo

[WISE' 2020] MULCE: Multi-level Canonicalization with Embeddings of Open Knowledge Bases [Paper]

Tien-Hsuan Wu, Ben Kao, Zhiyong Wu, Xiyang Feng, Qianli Song, Cheng Chen

[CoRR' 2020] Canonicalizing Open Knowledge Bases with Multi-Layered Meta-Graph Neural Network [Paper]

Tianwen Jiang, Tong Zhao, Bing Qin, Ting Liu, Nitesh V. Chawla, Meng Jiang

[ICDE' 2019] Canonicalization of Open Knowledge Bases with Side Information from the Source Text [Paper | Code | Dataset Description]

Xueling Lin, Lei Chen

[WWW' 2018] CESI: Canonicalizing Open Knowledge Bases using Embeddings and Side Information [Paper | Code]

Shikhar Vashishth, Prince Jain, Partha Talukdar

[CIKM' 2018] Towards Practical Open Knowledge Base Canonicalization [Paper]

Tien-Hsuan Wu, Zhiyong Wu, Ben Kao, Pengcheng Yin

[CIKM' 2014] Canonicalizing Open Knowledge Bases [Paper]

Luis Galárraga, Geremy Heitz, Kevin Murphy, Fabian M. Suchanek

Open Knowledge Graph Link Prediction

[ACL' 2021] OKGIT: Open Knowledge Graph Link Prediction with Implicit Types [Paper | Code | Video]

Chandrahas, Partha Pratim Talukdar

[ACL' 2020] Can We Predict New Facts with Open Knowledge Graph Embeddings? A Benchmark for Open Link Prediction [Paper | Code | Resources | Video]

Samuel Broscheit, Kiril Gashteovski, Yanjie Wang, Rainer Gemulla

[EMNLP' 2019].CaRe: Open Knowledge Graph Embeddings [Paper | Code]

Swapnil Gupta, Sreyash Kenkre, Partha Talukdar

Open Knowledge Graph Reasoning

[EMNLP' 2019] Collaborative Policy Learning for Open Knowledge Graph Reasoning [Paper | Code]

Cong Fu, Tong Chen, Meng Qu, Woojeong Jin, Xiang Ren

Open Knowledge Graph Alignment

[Eval4NLP@EMNLP' 2020] On Aligning OpenIE Extractions with Knowledge Bases: A Case Study [Paper | Resources | Video | Slides]

Kiril Gashteovski, Rainer Gemulla, Bhushan Kotnis, Sven Hertling, Christian Meilicke

OKGs for downstream applications

OKG's output has been shown to be a useful input for many downstream tasks. In this section, several downstream tasks that benefited from OKG output are listed.

Entity and Relation Linking

[ICDE' 2021] CaSIE: Canonicalize and Informative Selection of the OpenIE system [Paper]

Hao Xin, Xueling Lin, Lei Chen

[VLDB' 2020] KBPearl: A Knowledge Base Population System Supported by Joint Entity and Relation Linking [Paper | Code | Readme]

Xueling Lin, Haoyang Li, Hao Xin, Zijian Li, Lei Chen

Slides

Talks

Code

Data

OIE output is used as a useful input in many other downstream tasks, such as question answering, event schema induction or generating inference rules. Moreover, OIE output can be used as a "fuel" to derive further resources. Here, the data is organized into two major categories: 1) OIE corpora; 2) Resources derived from OIE output.

OIE corpora

  • OPIEC: An Open Information Extraction Corpus: the largest OIE corpus to date, containing more than 341M triples extracted from the entire English Wikipedia. Each triple from the corpus is composed of rich meta-data: each token from the subj / obj / rel along with NLP annotations (POS tag, NER tag, ...), provenance sentence along with the dependency parse, original (golden) left from Wikipedia, sentence order, space / time, etc.
  • [.gz] ReVerb extractions: 15 million high-precision OIE extractions (826MB compressed) from the OIE system ReVerb. The extractions were made from the ClueWeb09 corpus. The data contains (subject, relation, object) triples, accompanied by a confidence score (estimating the likelihood of whether the triple was correctly extracted) and provenance information (the link of the web-page where the triple was extracted from).
  • ReVerb extractions (linked): 3 million triples with linked argument (a subset of the 15 M high-precision ReVerb extractions). The links (to Freebase) are provided by an entity linker. The data fields are: argument 1, relation phrase, argument 2, freebase ID for argument 1 link, corresponding freebase entity name, link score, link ambiguity score
  • PATTY: PATTY is a system that takes open relations between two arguments, structures them into relational synsets and then organizes the synsets into a taxonomy. This resource contains over 15M triples with disambiguated arguments (links to WikiPedia articles) and relation synset ID between them. Additionaly, the resource contains: 1) relation pattern synsets with type signatures; 2) relation pattern subsumptions; 3) relation paraphrases; 4) evaluation data;
  • WiseNet (1.0 and 2.0): similarly as PATTY, WiseNet 1.0/2.0 is a source containing of OIE triples, where the arguments are disambiguated and the open relations are organized into relation synsets and then taxonomized. One of the main differences between PATTY and WiseNet is that WiseNet contains "golden links" for the arguments (annotated by humans) by keeping the original links from the WikiPedia articles.
  • KB-Unify: KB-Unify takes as an input several OIE corpora and unifies them into a single disambiguated OIE repository. The open relations are organized into relational synsets and the arguments are disambiguated with BabelFy.

Other Repos

About

A collection of important open knowledge graph (OKG) construction, canonicalization and representation learning papers with implementations.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published