Enhancing taxonomy completion with concept generation via fusing relational representations

Q Zeng, J Lin, W Yu, J Cleland-Huang… - Proceedings of the 27th …, 2021 - dl.acm.org
Automatic construction of a taxonomy supports many applications in e-commerce, web
search, and question answering. Existing taxonomy expansion or completion methods …

Steam: Self-supervised taxonomy expansion with mini-paths

Y Yu, Y Li, J Shen, H Feng, J Sun… - Proceedings of the 26th …, 2020 - dl.acm.org
Taxonomies are important knowledge ontologies that underpin numerous applications on a
daily basis, but many taxonomies used in practice suffer from the low coverage issue. We …

Which is better? Taxonomy induction with learning the optimal structure via contrastive learning

Y Meng, S Zhai, Z Chai, Y Zhang, T Wu, G Qi… - Knowledge-Based …, 2024 - Elsevier
A taxonomy represents a hierarchically structured knowledge graph that forms the
infrastructure for various downstream applications, including recommender systems, web …

Chain-of-layer: Iteratively prompting large language models for taxonomy induction from limited examples

Q Zeng, Y Bai, Z Tan, S Feng, Z Liang… - Proceedings of the 33rd …, 2024 - dl.acm.org
Automatic taxonomy induction is crucial for web search, recommendation systems, and
question answering. Manual curation of taxonomies is expensive in terms of human effort …

TEMP: taxonomy expansion with dynamic margin loss through taxonomy-paths

Z Liu, H Xu, Y Wen, N Jiang, H Wu… - Proceedings of the 2021 …, 2021 - aclanthology.org
As an essential form of knowledge representation, taxonomies are widely used in various
downstream natural language processing tasks. However, with the continuously rising of …

Constructing taxonomies from pretrained language models

C Chen, K Lin, D Klein - arxiv preprint arxiv:2010.12813, 2020 - arxiv.org
We present a method for constructing taxonomic trees (eg, WordNet) using pretrained
language models. Our approach is composed of two modules, one that predicts parenthood …

Enquire one's parent and child before decision: Fully exploit hierarchical structure for self-supervised taxonomy expansion

S Wang, R Zhao, X Chen, Y Zheng, B Liu - Proceedings of the Web …, 2021 - dl.acm.org
Taxonomy is a hierarchically structured knowledge graph that plays a crucial role in
machine intelligence. The taxonomy expansion task aims to find a position for a new term in …

Towards Visual Taxonomy Expansion

T Zhu, J Liu, J Liang, H Jiang, Y **ao, Z Wang… - Proceedings of the 31st …, 2023 - dl.acm.org
Taxonomy expansion task is essential in organizing the ever-increasing volume of new
concepts into existing taxonomies. Most existing methods focus exclusively on using textual …

Generating and visualizing trace link explanations

Y Liu, J Lin, O Anuyah, R Metoyer… - Proceedings of the 44th …, 2022 - dl.acm.org
Recent breakthroughs in deep-learning (DL) approaches have resulted in the dynamic
generation of trace links that are far more accurate than was previously possible. However …

Learning what you need from what you did: Product taxonomy expansion with user behaviors supervision

S Cheng, Z Gu, B Liu, R **e, W Wu… - 2022 IEEE 38th …, 2022 - ieeexplore.ieee.org
Taxonomies have been widely used in various domains to underpin numerous applications.
Specially, product taxonomies serve an essential role in the e-commerce domain for the …