Search Results - "Ok, Hyunjong"

Post-Trained Language Model Adaptive to Extractive Summarization of Long Spoken Documents by Ok, Hyunjong, Park, Seong-Bae

“…The General Meeting Understanding and Generation Challenge challenge track 2 in ICASSP 2023 Signal Processing Grand Challenge aims at extractive summarization…”
Get full text

FinTree: Financial Dataset Pretrain Transformer Encoder for Relation Extraction by Ok, Hyunjong

“…We present FinTree, Financial Dataset Pretrain Transformer Encoder for Relation Extraction. Utilizing an encoder language model, we further pretrain FinTree on…”
Get full text

Constructing a Singing Style Caption Dataset by Ok, Hyunjong, Lee, Jaeho

“…Singing voice synthesis and conversion have emerged as significant subdomains of voice generation, leading to much demands on prompt-conditioned generation…”
Get full text

AudioBERT: Audio Knowledge Augmented Language Model by Ok, Hyunjong, Yoo, Suho, Lee, Jaeho

“…Recent studies have identified that language models, pretrained on text-only datasets, often lack elementary visual knowledge, \textit{e.g.,} colors of…”
Get full text

Decoding with Limited Teacher Supervision Requires Understanding When to Trust the Teacher by Ok, Hyunjong, Ryu, Jegwang, Lee, Jaeho

“…How can small-scale large language models (LLMs) efficiently utilize the supervision of LLMs to improve their generative quality? This question has been well…”
Get full text

SCANNER: Knowledge-Enhanced Approach for Robust Multi-modal Named Entity Recognition of Unseen Entities by Ok, Hyunjong, Kil, Taeho, Seo, Sukmin, Lee, Jaeho

“…Recent advances in named entity recognition (NER) have pushed the boundary of the task to incorporate visual signals, leading to many variants, including…”
Get full text