Korean
PulseAugur coverage of Korean — every cluster mentioning Korean across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
Korean sentiment analysis boosted by new multiword expression resource
Researchers have developed DECO-MWE, a new linguistic resource for analyzing sentiment in Korean text, specifically focusing on multiword expressions (MWEs). This resource utilizes the Local Grammar Graph (LGG) methodol…
-
Korean linguistic resource FIAD aids banking chatbot NLU data generation
Researchers have developed FIAD, a Korean linguistic resource designed to generate Natural Language Understanding (NLU) training data for banking customer service dialog systems. By analyzing banking app reviews, they i…
-
Korean legal chatbot uses novel dataset generation for 91% accuracy
Researchers have developed a novel method for generating large, labeled datasets for Korean legal chatbots, addressing the challenge of high labeling costs. Their approach utilizes local grammar graphs (LGGs) to create …
-
L2 Korean annotation uses parser agreement for human-in-the-loop workflow
Researchers have developed a new human-in-the-loop annotation workflow for L2 Korean using agreement between two parsers. This method leverages parser agreement as a proxy for annotation correctness, showing strong corr…
-
New TTS system PS-TTS achieves natural automated dubbing with phonetic synchronization
Researchers have developed PS-TTS and PS-Comet TTS, new text-to-speech systems designed to improve automated dubbing by addressing synchronization challenges. These systems focus on matching speech duration to source au…
-
Korean legal LLM LegalMidm developed with focus on real-world use cases
Researchers have developed LegalMidm, a specialized large language model tailored for the Korean legal domain. This model was created using a systematic training framework that prioritizes practical legal use cases and …
-
XITE technique boosts cross-lingual transfer for language models up to 81%
Researchers have introduced XITE, a novel data augmentation technique designed to improve cross-lingual transfer in multilingual language models. This method leverages embedding similarities to identify and adapt labels…
-
Korean aegyo speech mimics childlike vocalizations by raising F1 values
A recent study published on arXiv investigated the linguistic phenomenon of Korean aegyo, a childlike speaking style used in romantic contexts. Researchers analyzed speech patterns from twelve Seoul Korean speakers, com…
-
K-MetBench benchmark evaluates AI's meteorological reasoning and multimodality
Researchers have developed K-MetBench, a new benchmark designed to evaluate AI models' capabilities in meteorology, focusing on expert reasoning, visual chart interpretation, and cultural context. The benchmark, derived…