Search Results for author:
Found 4 papers, 1 papers with code
AURA: Natural Language Reasoning for Aleatoric Uncertainty in Rationales
Thus, such reasoning tasks often compel models to output correct answers under undesirable rationales and are sub-optimal compared to what the models are fully capable of.
ATHENA: Mathematical Reasoning with Thought Expansion
Solving math word problems depends on how to articulate the problems, the lens through which models view human linguistic expressions.
Ranked #1 on
Math Word Problem Solving
on ASDiv-A
LST: Lexicon-Guided Self-Training for Few-Shot Text Classification
Self-training provides an effective means of using an extremely small amount of labeled data to create pseudo-labels for unlabeled data.
ALP: Data Augmentation using Lexicalized PCFGs for Few-Shot Text Classification
Taken together, our contributions on the data augmentation strategies yield a strong training recipe for few-shot text classification tasks.
