Papers with OXMC

2 papers
From Lazy to Prolific: Tackling Missing Labels in Open Vocabulary Extreme Classification by Positive-Unlabeled Sequence Learning (2025.findings-naacl)

Copied to clipboard

Challenge: Extreme multi-label classification (OXMC) is a challenging and critical task in natural language processing.
Approach: They propose to use PUSL to reframe OXMC as an infinite keyphrase generation task . they propose to adopt evaluation metrics to reliably assess OXML models with incomplete ground truths.
Outcome: The proposed approach improves on a highly imbalanced e-commerce dataset with missing labels . it generates 30% more unique labels and 72% of its predictions align with actual user queries .
Open Vocabulary Extreme Classification Using Generative Models (2022.findings-acl)

Copied to clipboard

Challenge: Extreme multi-label classification (XMC) aims at tagging content with subset of labels from an extremely large label set.
Approach: They propose a model that predicts a set of labels outside of the known vocabulary by using a loss-dependent loss-based loss-free model.
Outcome: The proposed model can predict labels outside the known vocabulary while performing on par with state-of-the-art solutions for known labels.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations