Self-Training using Rules of Grammar for Few-Shot NLU

no code implementations • Findings (EMNLP) 2021 • Joonghyuk Hahn, Hyunjoon Cheon, Kyuyeol Han, Cheongjae Lee, Junseok Kim, Yo-Sub Han

We propose to use rules of grammar in self-training as a more reliable pseudo-labeling mechanism, especially when there are few labeled data.

Boosting Code Summarization by Embedding Code Structures

1 code implementation • COLING 2022 • Jikyoeng Son, Joonghyuk Hahn, HyeonTae Seo, Yo-Sub Han

We find that a program dependency graph (PDG) can represent the structure of a code more effectively.

Code Summarization Graph Embedding

ATHENA: Mathematical Reasoning with Thought Expansion

1 code implementation • EMNLP 2023 • JB. Kim, Hazel Kim, Joonghyuk Hahn, Yo-Sub Han

Solving math word problems depends on how to articulate the problems, the lens through which models view human linguistic expressions.

Math Math Word Problem Solving