output
20192022
most citedAccelerating RNN Transducer Inference via One-Step Constrained Beam Search

21 citations

5 papers

cs.CL2022★ 2 cited

LittleBird: Efficient Faster & Longer Transformer for Question Answering

Minchul Lee, Kijong Han, Myeong Cheol Shin

BERT has shown a lot of sucess in a wide variety of NLP tasks. But it has a limitation dealing with long inputs due to its attention mechanism. Longformer, ETC and BigBird addresse…

cs.LG2021★ 21 cited

Connecting Low-Loss Subspace for Personalized Federated Learning

Seok-Ju Hahn, Minwoo Jeong, Junghye Lee

Due to the curse of statistical heterogeneity across clients, adopting a personalized federated learning method has become an essential choice for the successful deployment of fede…

cs.CL2020★ 3 cited

Integrated Eojeol Embedding for Erroneous Sentence Classification in Korean Chatbots

DongHyun Choi, IlNam Park, Myeong Cheol Shin +2

This paper attempts to analyze the Korean sentence classification system for a chatbot. Sentence classification is the task of classifying an input sentence based on predefined cat…

cs.LG2020★ 21 cited

Accelerating RNN Transducer Inference via One-Step Constrained Beam Search

Juntae Kim, Yoonhan Lee

We propose a one-step constrained (OSC) beam search to accelerate recurrent neural network (RNN) transducer (RNN-T) inference. The original RNN-T beam search has a while-loop leadi…

cs.LG2019★ 5 cited

A Plug-in Method for Representation Factorization in Connectionist Models

Jee Seok Yoon, Myung-Cheol Roh, Heung-Il Suk

In this article, we focus on decomposing latent representations in generative adversarial networks or learned feature representations in deep autoencoders into semantically control…