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.

Neuro-Symbolic Regex Synthesis Framework via Neural Example Splitting

no code implementations • 20 May 2022 • Su-Hyeon Kim, Hyunjoon Cheon, Yo-Sub Han, Sang-Ki Ko

We tackle the problem of learning regexes faster from positive and negative strings by relying on a novel approach called `neural example splitting'.

SplitRegex: Faster Regex Synthesis via Neural Example Splitting

no code implementations • 29 Sep 2021 • Su-Hyeon Kim, Hyunjoon Cheon, Yo-Sub Han, Sang-Ki Ko

SplitRegex is a divided-and-conquer framework for learning target regexes; split (=divide) positive strings and infer partial regexes for multiple parts, which is much more accurate than the whole string inferring, and concatenate (=conquer) inferred regexes while satisfying negative strings.

OPERA: Reasoning about continuous common knowledge in asynchronous distributed systems

no code implementations • 4 Oct 2018 • Sang-Min Choi, Jiho Park, Quan Nguyen, Andre Cronje, Kiyoung Jang, Hyunjoon Cheon, Yo-Sub Han, Byung-Ik Ahn

Each event block is signed by the hashes of the creating node and its $k$ peers.

Distributed, Parallel, and Cluster Computing