Summary of Extreme Multi-label Completion For Semantic Document Labelling with Taxonomy-aware Parallel Learning, by Julien Audiffren et al.
Extreme Multi-label Completion for Semantic Document Labelling with Taxonomy-Aware Parallel Learning
by Julien Audiffren, Christophe Broillet, Ljiljana Dolamic, Philippe Cudré-Mauroux
First submitted to arxiv on: 18 Dec 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed approach, TAMLEC (Taxonomy-Aware Multi-task Learning for Extreme multi-label Completion), tackles the challenging problem of predicting missing labels in a collection of documents. By dividing the task into subsets adapted to hierarchical paths of the taxonomy, TAMLEC leverages taxonomy-aware tasks using dynamic parallel feature sharing. This allows the model to predict ordered sequences of labels on a Weak-Semilattice structure induced by tasks. The approach outperforms state-of-the-art methods for various XMLCo problems and demonstrates strong performance in few-shot XML tasks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary TAMLEC is a new way to solve a really hard problem called Extreme Multi Label Completion (XMLCo). This problem involves predicting missing labels on many documents, where there are thousands of possible labels. The approach uses special subsets of labels that match the hierarchy of the taxonomy and trains models to complete these tasks together. This helps the model predict the correct labels even when it’s given very few examples. |
Keywords
» Artificial intelligence » Few shot » Multi task
