23 citations · 29 across the 12 of their papers we have counts for
12 papers
Gradient Estimation for Unseen Domain Risk Minimization with Pre-Trained Models
Byounggyu Lew, Donghyun Son, Buru Chang
Domain generalization aims to build generalized models that perform well on unseen domains when only source domains are available for model optimization. Recent studies have shown…
Measuring and Improving Semantic Diversity of Dialogue Generation
Seungju Han, Beomsu Kim, Buru Chang
Response diversity has become an important criterion for evaluating the quality of open-domain dialogue generation models. However, current evaluation metrics for response diversit…
TiDAL: Learning Training Dynamics for Active Learning
Seong Min Kye, Kwanghee Choi, Hyeongmin Byun +1
Active learning (AL) aims to select the most useful data samples from an unlabeled data pool and annotate them to expand the labeled dataset under a limited budget. Especially, unc…
Reliable Decision from Multiple Subtasks through Threshold Optimization: Content Moderation in the Wild
Donghyun Son, Byounggyu Lew, Kwanghee Choi +5
Social media platforms struggle to protect users from harmful content through content moderation. These platforms have recently leveraged machine learning models to cope with the v…
Meet Your Favorite Character: Open-domain Chatbot Mimicking Fictional Characters with only a Few Utterances
Seungju Han, Beomsu Kim, Jin Yong Yoo +4
In this paper, we consider mimicking fictional characters as a promising direction for building engaging conversation models. To this end, we present a new practical task where onl…
Understanding and Improving the Exemplar-based Generation for Open-domain Conversation
Seungju Han, Beomsu Kim, Seokjun Seo +2
Exemplar-based generative models for open-domain conversation produce responses based on the exemplars provided by the retriever, taking advantage of generative models and retrieva…
Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrection
Seong Min Kye, Kwanghee Choi, Joonyoung Yi +1
Recent studies on learning with noisy labels have shown remarkable performance by exploiting a small clean dataset. In particular, model agnostic meta-learning-based label correcti…
Temporal Knowledge Distillation for On-device Audio Classification
Kwanghee Choi, Martin Kersner, Jacob Morton +1
Improving the performance of on-device audio classification models remains a challenge given the computational limits of the mobile environment. Many studies leverage knowledge dis…
Distilling the Knowledge of Large-scale Generative Models into Retrieval Models for Efficient Open-domain Conversation
Beomsu Kim, Seokjun Seo, Seungju Han +2
Despite the remarkable performance of large-scale generative models in open-domain conversation, they are known to be less practical for building real-time conversation systems due…
Efficient Click-Through Rate Prediction for Developing Countries via Tabular Learning
Joonyoung Yi, Buru Chang
Despite the rapid growth of online advertisement in developing countries, existing highly over-parameterized Click-Through Rate (CTR) prediction models are difficult to be deployed…
"Killing Me" Is Not a Spoiler: Spoiler Detection Model using Graph Neural Networks with Dependency Relation-Aware Attention Mechanism
Buru Chang, Inggeol Lee, Hyunjae Kim +1
Several machine learning-based spoiler detection models have been proposed recently to protect users from spoilers on review websites. Although dependency relations between context…
Disentangling Label Distribution for Long-tailed Visual Recognition
Youngkyu Hong, Seungju Han, Kwanghee Choi +3
The current evaluation protocol of long-tailed visual recognition trains the classification model on the long-tailed source label distribution and evaluates its performance on the…