no code implementations • 25 Mar 2024 • Dongjun Jang, Sungjoo Byun, Hyopil Shin
This study examines whether the attention scores between tokens in the BERT model significantly vary based on lexical categories during the fine-tuning process for downstream tasks.
no code implementations • 25 Mar 2024 • Dongjun Jang, Sungjoo Byun, Hyemi Jo, Hyopil Shin
Based on the its quality and empirical results, this paper proposes that \textit{KIT-19} has the potential to make a substantial contribution to the future improvement of Korean LLMs' performance.
no code implementations • 24 Mar 2024 • Sungjoo Byun, Jiseung Hong, Sumin Park, Dongjun Jang, Jean Seo, Minseok Kim, Chaeyoung Oh, Hyopil Shin
Named Entity Recognition (NER) plays a pivotal role in medical Natural Language Processing (NLP).
Medical Named Entity Recognition named-entity-recognition +2
no code implementations • 23 Feb 2024 • Dongjun Jang, Jean Seo, Sungjoo Byun, Taekyoung Kim, Minseok Kim, Hyopil Shin
In order to tackle these challenges, we introduce CARBD-Ko (a Contextually Annotated Review Benchmark Dataset for Aspect-Based Sentiment Classification in Korean), a benchmark dataset that incorporates aspects and dual-tagged polarities to distinguish between aspect-specific and aspect-agnostic sentiment classification.
no code implementations • 30 Nov 2023 • Sungjoo Byun, Dongjun Jang, Hyemi Jo, Hyopil Shin
Caution: this paper may include material that could be offensive or distressing.
no code implementations • 29 Nov 2023 • Jean Seo, Sungjoo Byun, Minha Kang, Sangah Lee
The Manchu language, with its roots in the historical Manchurian region of Northeast China, is now facing a critical threat of extinction, as there are very few speakers left.
no code implementations • 23 Nov 2023 • Dongjun Jang, Sangah Lee, Sungjoo Byun, Jinwoong Kim, Jean Seo, Minseok Kim, Soyeon Kim, Chaeyoung Oh, Jaeyoon Kim, Hyemi Jo, Hyopil Shin
This paper presents the DaG LLM (David and Goliath Large Language Model), a language model specialized for Korean and fine-tuned through Instruction Tuning across 41 tasks within 13 distinct categories.