awesome-taxonomy

A curated resource for taxonomy research

Datasets / Shared Tasks

1. SemEval-2015 Task 17: Taxonomy Extraction Evaluation (TExEval-1), Home, Report

2. SemEval-2016 Task 13: Taxonomy Extraction Evaluation (TExEval-2), Home, Report

3. SemEval-2016 Task 14: Semantic Taxonomy Enrichment, Home, Report

4. SemEval-2018 Task 9: Hypernym Discovery, Home, Report

5. UnsupervisedHypernymy, Home, EACL 2017 paper, including 4 datasets:

   • (Hypernymy Detection): EVAL, BLESS, LEDS (a.k.a Lenci/Benotto), Weeds

6. HypernymySuite, Home, ACL 2018 paper, including (somewhat modified) datasets:

   • (Hypernymy Detection): BLESS, LEDS, EVAL, SHWARTZ, WBLESS
   • (Hypernymy Direction): BLESS, WBLESS, BIBLESS
   • (Graded Entailment): HyperLex

Paper

Book & Survey & Tutorials

• [ACL 2017] A Short Survey on Taxonomy Learning from Text Corpora: Issues, Resources and Recent Advances

• [ICDM 2021] Automated Taxonomy Discovery and Exploration

  • Slides: https://drive.google.com/drive/folders/1e_wb0MWydNPSEtZGD6g8ZLM-5Q_OtQdh

• [Springer Nature 2022] Automated Taxonomy Discovery and Exploration

Hypernymy Discovery & Lexical Entailment

• [IJCAI 2015] Learning Term Embeddings for Hypernymy Identification
• [ACL 2016] Improving Hypernymy Detection with an Integrated Path-based and Distributional Method (HypeNet)
  • Code: https://github.com/vered1986/HypeNET
• [COLING 2016 CogALex-V] LexNET -- Integrated Path-based and Distributional Method for the Identification of Semantic Relations
  • Code: https://github.com/vered1986/LexNET
• [SemEval 2016] TAXI at SemEval-2016 Task 13: a Taxonomy Induction Method based on Lexico-Syntactic Patterns, Substrings and Focused Crawling
• [EMNLP 2016] Relations such as Hypernymy: Identifying and Exploiting Hearst Patterns in Distributional Vectors for Lexical Entailment
  • Code: https://github.com/stephenroller/emnlp2016
• [EMNLP 2016] Learning Term Embeddings for Taxonomic Relation Identification Using Dynamic Weighting Neural Network
• [EACL 2017] Hypernyms under Siege: Linguistically-motivated Artillery for Hypernymy Detection
  • Code: https://github.com/vered1986/UnsupervisedHypernymy
• [EMNLP 2017] Hierarchical Embeddings for Hypernymy Detection and Directionality (HyperVec)
  • Code: https://github.com/nguyenkh/HyperVec
• [NAACL 2018] Distributional Inclusion Vector Embedding for Unsupervised Hypernymy Detection
• [NAACL 2018] Specialising Word Vectors for Lexical Entailment
  • Code: https://github.com/nmrksic/lear
• [SEM 2018] Term Definitions Help Hypernymy Detection
• Hearst Patterns Revisited: Automatic Hypernym Detection from Large Text Corpora [ACL 2018]
  • Code: https://github.com/facebookresearch/hypernymysuite
• [AAAI 2019] Improving Hypernymy Prediction via Taxonomy Enhanced Adversarial Learning
  • Code: https://github.com/chywang/TEAL
• [WWW 2019] A Family of Fuzzy Orthogonal Projection Models for Monolingual and Cross-lingual Hypernymy Prediction
  • Code: https://github.com/chywang/FOP
• [CIKM 2019] Discovering Hypernymy in Text-Rich Heterogeneous Information Network by Exploiting Context Granularity
  • Code: https://github.com/ysyushi/HyperMine
• [AAAI 2020] Hypernym Detection Using Strict Partial Order Networks
• [ACL 2020] BiRRE: Learning Bidirectional Residual Relation Embeddings for Supervised Hypernymy Detection
• [ACL 2020] Hypernymy Detection for Low-Resource Languages via Meta Learning
• [EMNLP 2020] When Hearst Is not Enough: Improving Hypernymy Detection from Corpus with Distributional Models
  • Code: https://github.com/HKUST-KnowComp/ComHyper
• [ACL 2021 Findings] Hypernym Discovery via a Recurrent Mapping Model
• [ACL 2021 Findings] More than just Frequency? Demasking Unsupervised Hypernymy Prediction Method
  • Code: https://github.com/Thommy96/hyp-freq-comp
• [*SEM 2023] Seeking Clozure: Robust Hypernym Extraction from BERT with Anchored Prompts
  • Code: https://github.com/ChunhuaLiu596/AnchoredPrompts
• [EMNLP 2023] KEPL: Knowledge Enhanced Prompt Learning for Chinese Hypernym-Hyponym Extraction

Concept Taxonomy Construction (Instance-based Taxonomy)

• [ACL 2006] Semantic Taxonomy Induction from Heterogenous Evidence
• [AAAI 2007] Deriving a Large Scale Taxonomy from Wikipedia
• [ACL 2009] A Metric-based Framework for Automatic Taxonomy Induction
• [EMNLP 2010] A Semi-Supervised Method to Learn and Construct Taxonomies using the Web
• [CIKM 2010] MENTA: Inducing Multilingual Taxonomies from Wikipedia
• [IJCAI 2011] A graph-based algorithm for inducing lexical taxonomies from scratch
• [SIGMOD 2012] Probase: A probabilistic taxonomy for text understanding
• [ACL 2014]Learning Semantic Hierarchies via Word Embeddings
• [ACL 2014] Two Is Bigger (and Better) Than One -- the Wikipedia Bitaxonomy Project
  • Resources: http://wibitaxonomy.org/
• [ACL 2014] Structured Learning for Taxonomy Induction with Belief Propagation
• [EMNLP 2014] Taxonomy Construction Using Syntactic Contextual Evidence
• [EMNLP 2015] Incorporating Trustiness and Collective Synonym and Contrastive Evidence into Taxonomy Construction
• [ICDM 2015] Automatic Taxonomy Extraction from Bipartite Graphs
• [ACL 2016] Learning Concept Taxonomies from Multi-modal Data
• [COLING 2016] Revisiting Taxonomy Induction over Wikipedia
• [CIKM 2017] Taxonomy Induction using Hypernym Subsequences
• [NAACL 2018 ] Comparing Constraints for Taxonomic Organization
  • Code: https://github.com/acocos/tax-org
• [KDD 2018] HiExpan: Task-Guided Taxonomy Construction by Hierarchical Tree Expansion
  • Code: https://github.com/mickeystroller/HiExpan
• [ACL 2018] End-to-End Reinforcement Learning for Automatic Taxonomy Induction
  • Code: https://github.com/morningmoni/TaxoRL
• [ACL 2019] Inferring Concept Hierarchies from Text Corpora via Hyperbolic Embeddings
• [ACL 2020] Taxonomy Construction of Unseen Domains via Graph-based Cross-Domain Knowledge Transfer
  • Code: https://github.com/IBM/gnn-taxo-construction
• [NAACL 2021] Constructing Taxonomies from Pretrained Language Models
  • Code: https://github.com/cchen23/ctp
• [SEM 2022] Distilling Hypernymy Relations from Language Models: On the Effectiveness of Zero-Shot Taxonomy Induction
  • Code: https://github.com/devanshrj/zero-shot-taxonomy
• [Arxiv 2024] Chain-of-Layer: Iteratively Prompting Large Language Models for Taxonomy Induction from Limited Examples
  • Code: https://github.com/QingkaiZeng/Chain-of-Layer

Topic Taxonomy Construction (Clustering-based Taxonomy)

• [KDD 2012] Automatic Taxonomy Construction from Keywords
• [KDD 2013] A Phrase Mining Framework for Recursive Construction of a Topical Hierarchy
• [ACL 2015] Efficient Methods for Inferring Large Sparse Topic Hierarchies
• [KDD 2018] TaxoGen: Unsupervised Topic Taxonomy Construction by Adaptive Term Embedding and Clustering
  • Code: https://github.com/franticnerd/taxogen
• [WWW 2020] NetTaxo: Automated Topic Taxonomy Construction from Text-Rich Network
• [KDD 2020] CoRel: Seed-Guided Topical Taxonomy Construction by Concept Learning and Relation Transferring
  • Code: https://github.com/teapot123/CoRel

Taxonomy Expansion & Enrichment

• [CIKM 2012] A graph-based approach for ontology population with named entities
• [WWW 2014] A Hierarchical Dirichlet Model for Taxonomy Expansion for Search Engines
• [NAACL 2015] Reserating the awesometastic: An automatic extension of the WordNet taxonomy for novel terms
• [SemEval 2016] SemEval-2016 Task 14: Semantic Taxonomy Enrichment
• [SIGIR 2018] Enriching Taxonomies With Functional Domain Knowledge
• [ACL 2019] Every child should have parents: a taxonomy refinement algorithm based on hyperbolic term embeddings
  • Code: https://github.com/uhh-lt/Taxonomy_Refinement_Embeddings
• [ACL 2019] Automatic Taxonomy Induction and Expansion
• [AKBC 2019] Synonym Expansion for Large Shopping Taxonomies
• [WWW 2020] Expanding Taxonomies with Implicit Edge Semantics
  • Website w/ code, slides, video, etc.: https://cmuarborist.github.io/
• [WWW 2020] TaxoExpan: Self-supervised Taxonomy Expansion with Position-Enhanced Graph Neural Network
  • Code: https://github.com/mickeystroller/TaxoExpan
• [KDD 2020] STEAM: Self-Supervised Taxonomy Expansion with Mini-Paths
  • Code: https://github.com/yueyu1030/STEAM
• [KDD 2020] Octet: Online Catalog Taxonomy Enrichment with Self-Supervision
• [WWW-SSL 2021] Who Should Go First? A Self-Supervised Concept Sorting Model for Improving Taxonomy Expansion
• [AAAI 2021] Taxonomy Completion via Triplet Matching Network
  • Code: https://github.com/JieyuZ2/TMN
• [KDD 2021] Enhancing Taxonomy Completion with Concept Generation via Fusing Relational Representations
  • Code: https://github.com/QingkaiZeng/GenTaxo
• [WWW 2021] Enquire One’s Parent and Child Before Decision: Fully Exploit Hierarchical Structure for Self-Supervised Taxonomy Expansion
  • Code: https://github.com/sheryc/HEF
• [EMNLP 2021] TEMP: Taxonomy Expansion with Dynamic Margin Loss through Taxonomy-Paths
• [EMNLP 2021] Low-resource Taxonomy Enrichment with Pretrained Language Models
• [EMNLP Findings 2021] HyperExpan: Taxonomy Expansion with Hyperbolic Representation Learning
• [WWW 2022] TaxoEnrich: Self-Supervised Taxonomy Completion via Structure-Semantic Representations
• [WWW 2022] QEN: Applicable Taxonomy Completion via Evaluating Full Taxonomic Relations
• [WWW 2022] TaxoCom: Topic Taxonomy Completion with Hierarchical Discovery of Novel Topic Clusters
• [ICDE 2022] Learning What You Need from What You Did: Product Taxonomy Expansion with User Behaviors Supervision
  • Code: https://github.com/AdaCheng/Product_Taxonomy_Expansion
• [Semantic Web 2022] Taxonomy enrichment with text and graph vector representations
• [NAACL 2022] TEAM: A multitask learning based Taxonomy Expansion approach for Attach and Merge
• [IJCAI 2022] TaxoPrompt: A Prompt-based Generation Method with Taxonomic Context for Self-Supervised Taxonomy Expansion
• [EMNLP 2022] Topic Taxonomy Expansion via Hierarchy-Aware Topic Phrase Generation
• [AAAI 2023] DNG: Taxonomy Expansion by Exploring the Intrinsic Directed Structure on Non-Gaussian Space
• [WWW 2023] A Single Vector Is Not Enough: Taxonomy Expansion via Box Embeddings
  • Code: https://github.com/songjiang0909/BoxTaxo
• [WWW 2023] TaxoComplete: Self-Supervised Taxonomy Completion Leveraging Position-Enhanced Semantic Matching
  • Code: https://github.com/eXascaleInfolab/TaxoComplete
• [EACL 2023] Find Parent then Label Children: A Two-stage Taxonomy Completion Method with Pre-trained Language Model
  • Code: https://github.com/WENGSYX/ATTEMPT
• [EMNLP 2023] TacoPrompt: A Collaborative Multi-Task Prompt Learning Method for Self-Supervised Taxonomy Completion
  • Code: https://github.com/cyclexu/TacoPrompt
• [MM 2023] Towards Visual Taxonomy Expansion
  • Code: https://github.com/darthzhu/vte
• [WebConf 2024] Taxonomy Completion via Implicit Concept Insertion
  • Code: https://github.com/jingcshi/ICON
  • Talk: https://www.youtube.com/watch?v=9otF15bvuBc

Taxonomy Applications

Help Text Understanding and Representation Learning

• [SIGMOD 2012] Probase: A probabilistic taxonomy for text understanding
• [KDD 2019] Universal Representation Learning of Knowledge Bases by Jointly Embedding Instances and Ontological Concepts
  • Code: https://github.com/JunhengH/joie-kdd19
• [AKBC 2021] Manifold Alignment across Geometric Spaces for Knowledge Base Representation Learning
  • Code: https://github.com/HKUST-KnowComp/GeoAlign

Help Information Retrieval

• [WebConf 2024] Improving Retrieval in Theme-specific Applications using a Corpus Topical Taxonomy
  • Code: https://github.com/SeongKu-Kang/ToTER_WWW24
  • Talk: https://www.youtube.com/watch?v=Y7RU5GpgaEI

Help Network Embedding

• [KDD 2018] Hierarchical Taxonomy Aware Network Embedding
• [KDD 2018] On Interpretation of Network Embedding via Taxonomy Induction
  • Code: https://github.com/ninghaohello/UnderstandingNetworkEmbedding
• [ICDM 2020] Co-Embedding Network Nodes and Hierarchical Labels with Taxonomy Based Generative Adversarial Networks
  • Code: https://github.com/JieyuZ2/TaxoGAN

Improve Recommender System

• [CIKM 2004] Taxonomy-driven computation of product recommendations
• [VLDB 2012] Supercharging Recommender Systems using Taxonomies for Learning User Purchase Behavior
• [WSDM 2014] Taxonomy Discovery for Personalized Recommendation
• [WSDM 2019] Taxonomy-Aware Multi-Hop Reasoning Networks for Sequential Recommendation
  • Code: https://github.com/RUCDM/TMRN
• [KDD 2019] A User-Centered Concept Mining System for Query and Document Understanding at Tencent
  • Code: https://github.com/BangLiu/ConcepT
  • Code: https://github.com/JunhengH/joie-kdd19
• [CIKM 2019] STAR: Spatio-Temporal Taxonomy-Aware Tag Recommendation for Citizen Complaints
  • Code: https://github.com/jygao97/STAR
• [ICDE 2022] Enhancing Recommendation with Automated Tag Taxonomy Construction in Hyperbolic Space
  • Code: https://github.com/Melinda315/TaxoRec

Improve Information Extraction

• [ACL 2020] TXtract: Taxonomy-Aware Knowledge Extraction for Thousands of Product Categories
• [ACL 2021] OntoED: Low-resource Event Detection with Ontology Embedding
  • Code: https://github.com/231sm/Reasoning_In_EE
• [ACL 2021] OntoEA: Ontology-guided Entity Alignment via Joint Knowledge Graph Embedding
  • Code: https://github.com/ZihengZZH/OntoEA
• [EMNLP 2021] ChemNER: Fine-Grained Chemistry Named Entity Recognition with Ontology-Guided Distant Supervision
  • Code: https://github.com/xuanwang91/ChemNER
• [WWW 2022] Ontology-enhanced Prompt-tuning for Few-shot Learning
• [EMNLP 2023] Taxonomy Expansion for Named Entity Recognition

Guide Entity Translation

• [KDD 2022] TaxoTrans: Taxonomy-Guided Entity Translation

Joint Taxonomy Construction and Application

• [EMNLP 2012] Constructing Task-Specific Taxonomies for Document Collection Browsing
• [WWW 2019] TiFi: Taxonomy Induction for Fictional Domains
• [SIGMOD 2020] GIANT: Scalable Creation of a Web-scale Ontology
  • Code: https://github.com/BangLiu/GIANT

Misc

• [ACL 2022] CogTaskonomy: Cognitively Inspired Task Taxonomy Is Beneficial to Transfer Learning in NLP
• [ACL 2022] Better Language Model with Hypernym Class Prediction
  • Code: https://github.com/richardbaihe/robustLM
• [ACL 2023] ESCOXLM-R: Multilingual Taxonomy-driven Pre-training for the Job Market Domain
  • Code: https://github.com/mainlp/escoxlmr