Jung-Woo Ha

verfied profile

∙ 0 followers
NAVER Corp. ∙ Seoul National University

Executive Officer, Research Head of Clova at NAVER Corp.

Advisory member of the Public Data Strategy Committee, Prime Minister, Korea Government.

Reward Optimization for Neural Machine Translation with Learned Metrics

Neural machine translation (NMT) models are conventionally trained with ...
04/15/2021 ∙ by Raphael Shu, et al. ∙ 0 ∙ share

read it
Rainbow Memory: Continual Learning with a Memory of Diverse Samples

Continual learning is a realistic learning scenario for AI models. Preva...
03/31/2021 ∙ by Jihwan Bang, et al. ∙ 27 ∙ share

read it
Self-supervised Auxiliary Learning for Graph Neural Networks via Meta-Learning

In recent years, graph neural networks (GNNs) have been widely adopted i...
03/01/2021 ∙ by Dasol Hwang, et al. ∙ 0 ∙ share

read it
M2FN: Multi-step Modality Fusion for Advertisement Image Assessment

Assessing advertisements, specifically on the basis of user preferences ...
01/31/2021 ∙ by Kyung-Wha Park, et al. ∙ 0 ∙ share

read it
DialogBERT: Discourse-Aware Response Generation via Learning to Recover and Rank Utterances

Recent advances in pre-trained language models have significantly improv...
12/03/2020 ∙ by Xiaodong Gu, et al. ∙ 0 ∙ share

read it
Context-Aware Answer Extraction in Question Answering

Extractive QA models have shown very promising performance in predicting...
11/05/2020 ∙ by Yeon Seonwoo, et al. ∙ 7 ∙ share

read it
ST-BERT: Cross-modal Language Model Pre-training For End-to-end Spoken Language Understanding

Language model pre-training has shown promising results in various downs...
10/23/2020 ∙ by Minjeong Kim, et al. ∙ 0 ∙ share

read it
Which Strategies Matter for Noisy Label Classification? Insight into Loss and Uncertainty

Label noise is a critical factor that degrades the generalization perfor...
08/14/2020 ∙ by Wonyoung Shin, et al. ∙ 6 ∙ share

read it
Self-supervised Auxiliary Learning with Meta-paths for Heterogeneous Graphs

Graph neural networks have shown superior performance in a wide range of...
07/16/2020 ∙ by Dasol Hwang, et al. ∙ 26 ∙ share

read it
CareCall: a Call-Based Active Monitoring Dialog Agent for Managing COVID-19 Pandemic

Tracking suspected cases of COVID-19 is crucial to suppressing the sprea...
07/06/2020 ∙ by Sang-Woo Lee, et al. ∙ 13 ∙ share

read it
Efficient Active Learning for Automatic Speech Recognition via Augmented Consistency Regularization

The cost of labeling transcriptions for large speech corpora becomes a b...
06/19/2020 ∙ by Jihwan Bang, et al. ∙ 0 ∙ share

read it
Slowing Down the Weight Norm Increase in Momentum-based Optimizers

Normalization techniques, such as batch normalization (BN), have led to ...
06/15/2020 ∙ by Byeongho Heo, et al. ∙ 16 ∙ share

read it
Graphs, Entities, and Step Mixture

Existing approaches for graph neural networks commonly suffer from the o...
05/18/2020 ∙ by Kyuyong Shin, et al. ∙ 16 ∙ share

read it
ClovaCall: Korean Goal-Oriented Dialog Speech Corpus for Automatic Speech Recognition of Contact Centers

Automatic speech recognition (ASR) via call is essential for various app...
04/20/2020 ∙ by Jung-Woo Ha, et al. ∙ 2 ∙ share

read it
Modeling Musical Onset Probabilities via Neural Distribution Learning

Musical onset detection can be formulated as a time-to-event (TTE) or ti...
02/10/2020 ∙ by Jaesung Huh, et al. ∙ 0 ∙ share

read it
StarGAN v2: Diverse Image Synthesis for Multiple Domains

A good image-to-image translation model should learn a mapping between d...
12/04/2019 ∙ by Yunjey Choi, et al. ∙ 22 ∙ share

read it
Neural Approximation of an Auto-Regressive Process through Confidence Guided Sampling

We propose a generic confidence-based approximation that can be plugged ...
10/15/2019 ∙ by YoungJoon Yoo, et al. ∙ 16 ∙ share

read it
Which Ads to Show? Advertisement Image Assessment with Auxiliary Information via Multi-step Modality Fusion

Assessing aesthetic preference is a fundamental task related to human co...
10/06/2019 ∙ by Kyung-Wha Park, et al. ∙ 0 ∙ share

read it
Tripartite Heterogeneous Graph Propagation for Large-scale Social Recommendation

Graph Neural Networks (GNNs) have been emerging as a promising method fo...
07/24/2019 ∙ by Kyung-Min Kim, et al. ∙ 0 ∙ share

read it
Photorealistic Style Transfer via Wavelet Transforms

Recent style transfer models have provided promising artistic results. H...
03/23/2019 ∙ by Jaejun Yoo, et al. ∙ 56 ∙ share

read it
Phase-aware Speech Enhancement with Deep Complex U-Net

Most deep learning-based models for speech enhancement have mainly focus...
03/07/2019 ∙ by Hyeong-Seok Choi, et al. ∙ 0 ∙ share

read it
Large-Scale Answerer in Questioner's Mind for Visual Dialog Question Generation

Answerer in Questioner's Mind (AQM) is an information-theoretic framewor...
02/22/2019 ∙ by Sang-Woo Lee, et al. ∙ 0 ∙ share

read it
Multi-Domain Processing via Hybrid Denoising Networks for Speech Enhancement

We present a hybrid framework that leverages the trade-off between tempo...
12/21/2018 ∙ by Jang-Hyun Kim, et al. ∙ 0 ∙ share

read it
CHOPT : Automated Hyperparameter Optimization Framework for Cloud-Based Machine Learning Platforms

Many hyperparameter optimization (HyperOpt) methods assume restricted co...
10/08/2018 ∙ by Jinwoong Kim, et al. ∙ 0 ∙ share

read it
NSML: Meet the MLaaS platform with a real-world case study

The boom of deep learning induced many industries and academies to intro...
10/08/2018 ∙ by Hanjoo Kim, et al. ∙ 0 ∙ share

read it
Reinforcement Learning based Recommender System using Biclustering Technique

A recommender system aims to recommend items that a user is interested i...
01/17/2018 ∙ by Sungwoon Choi, et al. ∙ 0 ∙ share

read it
NSML: A Machine Learning Platform That Enables You to Focus on Your Models

Machine learning libraries such as TensorFlow and PyTorch simplify model...
12/16/2017 ∙ by Nako Sung, et al. ∙ 0 ∙ share

read it
Automatic Music Highlight Extraction using Convolutional Recurrent Attention Networks

Music highlights are valuable contents for music services. Most methods ...
12/16/2017 ∙ by Jung-Woo Ha, et al. ∙ 0 ∙ share

read it
Highrisk Prediction from Electronic Medical Records via Deep Attention Networks

Predicting highrisk vascular diseases is a significant issue in the medi...
11/30/2017 ∙ by You Jin Kim, et al. ∙ 0 ∙ share

read it
StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation

Recent studies have shown remarkable success in image-to-image translati...
11/24/2017 ∙ by Yunjey Choi, et al. ∙ 0 ∙ share

read it
Representation Learning of Music Using Artist Labels

Recently, feature representation by learning algorithms has drawn great ...
10/18/2017 ∙ by Jiyoung Park, et al. ∙ 0 ∙ share

read it
Energy-Based Sequence GANs for Recommendation and Their Connection to Imitation Learning

Recommender systems aim to find an accurate and efficient mapping from h...
06/28/2017 ∙ by Jaeyoon Yoo, et al. ∙ 0 ∙ share

read it
Dual Attention Networks for Multimodal Reasoning and Matching

We propose Dual Attention Networks (DANs) which jointly leverage visual ...
11/02/2016 ∙ by Hyeonseob Nam, et al. ∙ 0 ∙ share

read it
Hadamard Product for Low-rank Bilinear Pooling

Bilinear models provide rich representations compared with linear models...
10/14/2016 ∙ by Jin-Hwa Kim, et al. ∙ 0 ∙ share

read it
Multimodal Residual Learning for Visual QA

Deep neural networks continue to advance the state-of-the-art of image r...
06/05/2016 ∙ by Jin-Hwa Kim, et al. ∙ 0 ∙ share

read it

Jung-Woo Ha

Featured Co-authors