LexC-Gen: Generating Data for Extremely Low-Resource Languages with Large Language Models and Bilingual Lexicons
Paper
•
2402.14086
•
Published
•
12
Cristina Menghini
crimenghini
AI & ML interests
Fine-tuning large pre-trained models on downstream tasks in settings with limited labeled data. Strong interest in the understanding of structured knowledge encoded by large models.
Organizations
authored
a
paper
almost 2 years ago
authored
6
papers
over 2 years ago
Enhancing CLIP with CLIP: Exploring Pseudolabeling for Limited-Label Prompt Tuning
Paper
•
2306.01669
•
Published
Tight Lower Bounds on Worst-Case Guarantees for Zero-Shot Learning with Attributes
Paper
•
2205.13068
•
Published
TAGLETS: A System for Automatic Semi-Supervised Learning with Auxiliary Data
Paper
•
2111.04798
•
Published
RePBubLik: Reducing the Polarized Bubble Radius with Link Insertions
Paper
•
2101.04751
•
Published
How Inclusive Are Wikipedia's Hyperlinks in Articles Covering Polarizing Topics?
Paper
•
2007.08197
•
Published
The Drift of #MyBodyMyChoice Discourse on Twitter
Paper
•
2205.04898
•
Published