Won Ik Cho
YOU?
Author Swipe
View article: Improving VR Welding Simulator Tracking Accuracy Through IMU-SLAM Fusion
Improving VR Welding Simulator Tracking Accuracy Through IMU-SLAM Fusion Open
Virtual reality (VR) welding simulators provide safe and cost-effective training environments, but precise torch tracking remains a key challenge. Current commercial systems are limited in accurate bead simulation and posture feedback due …
View article: A prompt framework for enhancing LLM-based explainability of medical machine learning models: an intensive care unit application
A prompt framework for enhancing LLM-based explainability of medical machine learning models: an intensive care unit application Open
Background Explainable AI (XAI) techniques like SHAP provide valuable insights into machine learning model predictions by quantifying feature contributions. However, interpreting these quantitative outputs remains unintuitive for many clin…
View article: Evaluating the Influence of Demographic Identity in the Medical Use of Large Language Models
Evaluating the Influence of Demographic Identity in the Medical Use of Large Language Models Open
As large language models (LLMs) are increasingly adopted in medical decision-making, concerns about demographic biases in AIgenerated recommendations remain unaddressed. In this study, we systematically investigate how demographic attribut…
View article: RICoTA: Red-teaming of In-the-wild Conversation with Test Attempts
RICoTA: Red-teaming of In-the-wild Conversation with Test Attempts Open
User interactions with conversational agents (CAs) evolve in the era of heavily guardrailed large language models (LLMs). As users push beyond programmed boundaries to explore and build relationships with these systems, there is a growing …
View article: Novel Deep Learning-Based Vocal Biomarkers for Stress Detection in Koreans
Novel Deep Learning-Based Vocal Biomarkers for Stress Detection in Koreans Open
Objective The rapid societal changes have underscored the importance of effective stress detection and management. Chronic mental stress significantly contributes to both physical and psychological illnesses. However, many individuals ofte…
View article: Well-Tempered Medical Prompt Engineering for Explainable Extubation
Well-Tempered Medical Prompt Engineering for Explainable Extubation Open
This study investigated whether the large language model (LLM) utilizes sufficient domain knowledge to reason about critical medical events such as extubation. In detail, we tested whether the LLM accurately comprehends given tabular data …
View article: Study on the Domain Adaption of Korean Speech Act using Daily Conversation Dataset and Petition Corpus
Study on the Domain Adaption of Korean Speech Act using Daily Conversation Dataset and Petition Corpus Open
In Korean, quantitative speech act studies have usually been conducted on single utterances with unspecified sources. In this study, we annotate sentences from the National Institute of Korean Language's Messenger Corpus and the National P…
View article: Evaluating Span Extraction in Generative Paradigm: A Reflection on Aspect-Based Sentiment Analysis
Evaluating Span Extraction in Generative Paradigm: A Reflection on Aspect-Based Sentiment Analysis Open
In the era of rapid evolution of generative language models within the realm of natural language processing, there is an imperative call to revisit and reformulate evaluation methodologies, especially in the domain of aspect-based sentimen…
View article: Three Disclaimers for Safe Disclosure: A Cardwriter for Reporting the Use of Generative AI in Writing Process
Three Disclaimers for Safe Disclosure: A Cardwriter for Reporting the Use of Generative AI in Writing Process Open
Generative artificial intelligence (AI) and large language models (LLMs) are increasingly being used in the academic writing process. This is despite the current lack of unified framework for reporting the use of machine assistance. In thi…
View article: Advancing Mental Health Diagnostics: A Novel Deep Learning Approach to Vocal Biomarker Identification for Stress Detection in a Korean Population (Preprint)
Advancing Mental Health Diagnostics: A Novel Deep Learning Approach to Vocal Biomarker Identification for Stress Detection in a Korean Population (Preprint) Open
BACKGROUND Escalating mental health concerns exacerbated by the coronavirus disease (COVID-19) and rapid societal shifts have made efficient monitoring of mental stress crucial. Chronic mental stress affects physical and psychological hea…
View article: PaperCard for Reporting Machine Assistance in Academic Writing
PaperCard for Reporting Machine Assistance in Academic Writing Open
Academic writing process has benefited from various technological developments over the years including search engines, automatic translators, and editing tools that review grammar and spelling mistakes. They have enabled human writers to …
View article: When Crowd Meets Persona: Creating a Large-Scale Open-Domain Persona Dialogue Corpus
When Crowd Meets Persona: Creating a Large-Scale Open-Domain Persona Dialogue Corpus Open
Building a natural language dataset requires caution since word semantics is vulnerable to subtle text change or the definition of the annotated concept. Such a tendency can be seen in generative tasks like question-answering and dialogue …
View article: Acoustic Analysis of Speech for Screening for Suicide Risk: Machine Learning Classifiers for Between- and Within-Person Evaluation of Suicidality
Acoustic Analysis of Speech for Screening for Suicide Risk: Machine Learning Classifiers for Between- and Within-Person Evaluation of Suicidality Open
Background Assessing a patient’s suicide risk is challenging for health professionals because it depends on voluntary disclosure by the patient and often has limited resources. The application of novel machine learning approaches to determ…
View article: Acoustic Analysis of Speech for Screening for Suicide Risk: Machine Learning Classifiers for Between- and Within-Person Evaluation of Suicidality (Preprint)
Acoustic Analysis of Speech for Screening for Suicide Risk: Machine Learning Classifiers for Between- and Within-Person Evaluation of Suicidality (Preprint) Open
BACKGROUND Assessing a patient’s suicide risk is challenging for health professionals because it depends on voluntary disclosure by the patient and often has limited resources. The application of novel machine learning approaches to deter…
View article: Detection of Depression and Suicide Risk Based on Text From Clinical Interviews Using Machine Learning: Possibility of a New Objective Diagnostic Marker
Detection of Depression and Suicide Risk Based on Text From Clinical Interviews Using Machine Learning: Possibility of a New Objective Diagnostic Marker Open
Background Depression and suicide are critical social problems worldwide, but tools to objectively diagnose them are lacking. Therefore, this study aimed to diagnose depression through machine learning and determine whether it is possible …
View article: Text Implicates Prosodic Ambiguity: A Corpus for Intention Identification of the Korean Spoken Language
Text Implicates Prosodic Ambiguity: A Corpus for Intention Identification of the Korean Spoken Language Open
Phonetic features are indispensable in understanding the spoken language. Especially in Korean, which is wh-in-situ and head-final, the addressee of spoken language sometimes finds it hard to discern the speaker’s original intention if not…
View article: "Feels like I've known you forever": empathy and self-awareness in human open-domain dialogs
"Feels like I've known you forever": empathy and self-awareness in human open-domain dialogs Open
As conversational agents become more human-like, people expect them to be engaging as well. However, developing agents that comprehend human desires and generate appropriate responses, continues to be a challenge. We, therefore, conducted …
View article: DAGAM: Data Augmentation with Generation And Modification
DAGAM: Data Augmentation with Generation And Modification Open
Text classification is a representative downstream task of natural language processing, and has exhibited excellent performance since the advent of pre-trained language models based on Transformer architecture. However, in pre-trained lang…
View article: APEACH: Attacking Pejorative Expressions with Analysis on Crowd-Generated Hate Speech Evaluation Datasets
APEACH: Attacking Pejorative Expressions with Analysis on Crowd-Generated Hate Speech Evaluation Datasets Open
In hate speech detection, developing training and evaluation datasets across various domains is the critical issue. Whereas, major approaches crawl social media texts and hire crowd-workers to annotate the data. Following this convention o…
View article: APEACH: Attacking Pejorative Expressions with Analysis on Crowd-Generated Hate Speech Evaluation Datasets
APEACH: Attacking Pejorative Expressions with Analysis on Crowd-Generated Hate Speech Evaluation Datasets Open
In hate speech detection, developing training and evaluation datasets across various domains is the critical issue. Whereas, major approaches crawl social media texts and hire crowd-workers to annotate the data. Following this convention o…
View article: kosp2e: Korean Speech to English Translation Corpus
kosp2e: Korean Speech to English Translation Corpus Open
Most speech-to-text (S2T) translation studies use English speech as a source, which makes it difficult for non-English speakers to take advantage of the S2T technologies. For some languages, this problem was tackled through corpus construc…
View article: KLUE: Korean Language Understanding Evaluation
KLUE: Korean Language Understanding Evaluation Open
We introduce Korean Language Understanding Evaluation (KLUE) benchmark. KLUE is a collection of 8 Korean natural language understanding (NLU) tasks, including Topic Classification, SemanticTextual Similarity, Natural Language Inference, Na…
View article: StyleKQC: A Style-Variant Paraphrase Corpus for Korean Questions and\n Commands
StyleKQC: A Style-Variant Paraphrase Corpus for Korean Questions and\n Commands Open
Paraphrasing is often performed with less concern for controlled style\nconversion. Especially for questions and commands, style-variant paraphrasing\ncan be crucial in tone and manner, which also matters with industrial\napplications such…
View article: Towards Cross-Lingual Generalization of Translation Gender Bias
Towards Cross-Lingual Generalization of Translation Gender Bias Open
Cross-lingual generalization issues for less explored languages have been broadly tackled in recent NLP studies. In this study, we apply the philosophy on the problem of translation gender bias, which necessarily involves multilingualism a…
View article: Google-trickers, Yaminjeongeum, and Leetspeak: An Empirical Taxonomy for Intentionally Noisy User-Generated Text
Google-trickers, Yaminjeongeum, and Leetspeak: An Empirical Taxonomy for Intentionally Noisy User-Generated Text Open
WARNING: This article contains contents that may offend the readers. Strategies that insert intentional noise into text when posting it are commonly observed in the online space, and sometimes they aim to let only certain community users u…
View article: VUS at IWSLT 2021: A Finetuned Pipeline for Offline Speech Translation
VUS at IWSLT 2021: A Finetuned Pipeline for Offline Speech Translation Open
In this technical report, we describe the fine-tuned ASR-MT pipeline used for the IWSLT shared task. We remove less useful speech samples by checking WER with an ASR model, and further train a wav2vec and Transformers-based ASR module base…
View article: Modeling the Influence of Verb Aspect on the Activation of Typical Event Locations with BERT
Modeling the Influence of Verb Aspect on the Activation of Typical Event Locations with BERT Open
Prior studies on event knowledge in sentence comprehension have shown that the aspect of the main verb plays an important role in the processing of non-core semantic roles, such as locations: when the aspect of the main verb is imperfectiv…
View article: Speech to Text Adaptation: Towards an Efficient Cross-Modal Distillation
Speech to Text Adaptation: Towards an Efficient Cross-Modal Distillation Open
Speech is one of the most effective means of communication and is full of information that helps the transmission of utterer's thoughts. However, mainly due to the cumbersome processing of acoustic features, phoneme or word posterior proba…
View article: BEEP! Korean Corpus of Online News Comments for Toxic Speech Detection
BEEP! Korean Corpus of Online News Comments for Toxic Speech Detection Open
Toxic comments in online platforms are an unavoidable social issue under the cloak of anonymity. Hate speech detection has been actively done for languages such as English, German, or Italian, where manually labeled corpus has been release…