Lune

EMNLP Findings2022

Topic Taxonomy Expansion via Hierarchy-Aware Topic Phrase Generation

Dongha Lee, Jiaming Shen, Seonghyeon Lee, Susik Yoon, Hwanjo Yu, Jiawei Han

Abstract

Topic taxonomies display hierarchical topic structures of a text corpus and provide topical knowledge to enhance various NLP applications. To dynamically incorporate new topic information, several recent studies have tried to expand (or complete) a topic taxonomy by inserting emerging topics identified in a set of new documents. However, existing methods focus only on frequent terms in documents and the local topic-subtopic relations in a taxonomy, which leads to limited topic term coverage and fails to model the global topic hierarchy. In this work, we propose a novel framework for topic taxonomy expansion, named Topic-Expan, which directly generates topic-related terms belonging to new topics. Specifically, TopicExpan leverages the hierarchical relation structure surrounding a new topic and the textual content of an input document for topic term generation. This approach encourages newly-inserted topics to further cover important but less frequent terms as well as to keep their relation consistency within the taxonomy. Experimental results on two real-world text corpora show that TopicExpan significantly outperforms other baseline methods in terms of the quality of output taxonomies.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

4 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • TaxoCom: Topic Taxonomy Completion with Hierarchical Discovery of Novel Topic Clusters cites Enhancing Taxonomy Completion with Concept Generation via Fusing Relational Representations
  • TaxoCom: Topic Taxonomy Completion with Hierarchical Discovery of Novel Topic Clusters cites NetTaxo: Automated Topic Taxonomy Construction from Text-Rich Network
  • TaxoCom: Topic Taxonomy Completion with Hierarchical Discovery of Novel Topic Clusters cites Hierarchical Topic Mining via Joint Spherical Tree and Text Embedding
  • Enhancing Taxonomy Completion with Concept Generation via Fusing Relational Representations cites NetTaxo: Automated Topic Taxonomy Construction from Text-Rich Network
  • Enhancing Taxonomy Completion with Concept Generation via Fusing Relational Representations cites TaxoExpan: Self-supervised Taxonomy Expansion with Position-Enhanced Graph Neural Network
  • Improving Retrieval in Theme-specific Applications using a Corpus Topical Taxonomy cites TaxoCom: Topic Taxonomy Completion with Hierarchical Discovery of Novel Topic Clusters
  • Improving Retrieval in Theme-specific Applications using a Corpus Topical Taxonomy cites NetTaxo: Automated Topic Taxonomy Construction from Text-Rich Network
  • Improving Retrieval in Theme-specific Applications using a Corpus Topical Taxonomy cites Hierarchical Topic Mining via Joint Spherical Tree and Text Embedding
  • TaxoAdapt: Aligning LLM-Based Multidimensional Taxonomy Construction to Evolving Research Corpora cites TaxoCom: Topic Taxonomy Completion with Hierarchical Discovery of Novel Topic Clusters
  • TaxoAdapt: Aligning LLM-Based Multidimensional Taxonomy Construction to Evolving Research Corpora cites NetTaxo: Automated Topic Taxonomy Construction from Text-Rich Network
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers4

  1. Improving Retrieval in Theme-specific Applications using a Corpus Topical TaxonomySeongKu Kang, Shivam Agarwal, Bowen Jin, Dongha Lee et al.WWW 2024 · 16 citations
  2. Constrained Non-negative Matrix Factorization for Guided Topic Modeling of Minority TopicsSeyedeh Fatemeh Ebrahimi, Jaakko PeltonenEMNLP 2025 · 2 citations
  3. MUDY: Multi-Granular Dynamic Candidate Contextualization for Unsupervised Keyphrase ExtractionHyeongu Kang, Susik YoonSIGIR 2026
  4. TaxoAdapt: Aligning LLM-Based Multidimensional Taxonomy Construction to Evolving Research CorporaPriyanka Kargupta, Nan Zhang, Yunyi Zhang, Rui Zhang et al.ACL 2025

Builds on8

  1. TaxoExpan: Self-supervised Taxonomy Expansion with Position-Enhanced Graph Neural NetworkJiaming Shen, Zhihong Shen, Chenyan Xiong, Chi Wang et al.WWW 2020 · 85 citations
  2. NetTaxo: Automated Topic Taxonomy Construction from Text-Rich NetworkJingbo Shang, Xinyang Zhang, Liyuan Liu, Sha Li et al.WWW 2020 · 66 citations
  3. Hierarchical Topic Mining via Joint Spherical Tree and Text EmbeddingYu Meng, Yunyi Zhang, Jiaxin Huang, Yu Zhang et al.KDD 2020 · 56 citations
  4. TaxoCom: Topic Taxonomy Completion with Hierarchical Discovery of Novel Topic ClustersDongha Lee, Jiaming Shen, Seongku Kang, Susik Yoon et al.WWW 2022 · 46 citations
  5. Enhancing Taxonomy Completion with Concept Generation via Fusing Relational RepresentationsQingkai Zeng, Jinfeng Lin, Wenhao Yu, Jane Cleland-Huang et al.KDD 2021 · 37 citations

Related papers

  1. Enquire One's Parent and Child Before Decision: Fully Exploit Hierarchical Structure for Self-Supervised Taxonomy ExpansionSuyuchen Wang, Ruihui Zhao, Xi Chen, Yefeng Zheng et al.WWW 2021 · 33 citations
  2. CoRel: Seed-Guided Topical Taxonomy Construction by Concept Learning and Relation TransferringJiaxin Huang, Yiqing Xie, Yu Meng, Yunyi Zhang et al.KDD 2020 · 27 citations
  3. TEMP: Taxonomy Expansion with Dynamic Margin Loss through Taxonomy-PathsZichen Liu, Hongyuan Xu, Yanlong Wen, Ning Jiang et al.EMNLP 2021 · 16 citations
  4. Knowledge-Aware Bayesian Deep Topic ModelDongsheng Wang, Yishi Xu, Miaoge Li, Zhibin Duan et al.NeurIPS 2022 · 19 citations
  5. HTKG: Deep Keyphrase Generation with Neural Hierarchical Topic GuidanceYuxiang Zhang, Tao Jiang, Tianyu Yang, Xiaoli Li et al.SIGIR 2022 · 14 citations
Dusk over the sea between two cliffs drawn in fine vertical lines