← Search

Chiyoun Park

2 accepted papers

2022

Injecting Logical Constraints into Neural Networks via Straight-Through Estimators

ICML 2022spotlight

Injecting discrete logical constraints into neural network learning is one of the main challenges in neuro-symbolic AI. We find that a straight-through-estimator, a method introduced to train binary neural networks, could effectively be applied to incorporate logical constraints into neural network…

2018

Accelerating Recurrent Neural Network Language Model Based Online Speech Recognition System

ICASSP 2018accepted

This paper presents methods to accelerate recurrent neural network based language models (RNNLMs) for online speech recognition systems. Firstly, a lossy compression of the past hidden layer outputs (history vector) with caching is introduced in order to reduce the number of LM queries. Next, RNNLM…

Cited by 0SourceScholar