conference paper

Vec2Node: Self-Training with Tensor Augmentation for Text Classification with Few Labels

Sara Abdali^a✉, Subhabrata Mukherjee^b, Evangelos E. Papalexakis^c

^aGeorgia Institute of Technology, Atlanta, USA
^bMicrosoft Research, Redmond, USA
^cUniversity of California, Riverside, USA
✉Corresponding author

Lecture notes in computer science Springer Science+Business Media2023-01-01 2 citations24 references

Looking for the full paper…

Export

Papers open inside SciRah from the original publisher or repository; SciRah never hosts them.

Abstract

No abstract is available from our sources. Use “Read paper” to view it.

TL;DRThis work develops Vec2Node that leverages self-training from in-domain unlabeled data augmented with tensorized word embeddings that significantly improves over state-of-the-art models, particularly in low-resource settings. (Semantic Scholar)

Plain-language summary

AI illustration of the topic of “Vec2Node: Self-Training with Tensor Augmentation for Text Classification with Few Labels”

Vec2Node: Self-Training with Tensor Augmentation for Text Classification with Few Labels

Abstract

Plain-language summary

Discussion