no code implementations • 20 Feb 2024 • Seanie Lee, Jianpeng Cheng, Joris Driesen, Alexandru Coca, Anders Johannsen
To address this problem, we handle the task of conversation retrieval based on text summaries of the conversations.
2 code implementations • 10 Oct 2023 • Dong Bok Lee, Seanie Lee, Joonho Ko, Kenji Kawaguchi, Juho Lee, Sung Ju Hwang
To achieve this, we also introduce the MSE between representations of the inner model and the self-supervised target model on the original full dataset for outer optimization.
no code implementations • 2 Oct 2023 • Seul Lee, Seanie Lee, Kenji Kawaguchi, Sung Ju Hwang
Additionally, the existing fragment-based generative models cannot update the fragment vocabulary with goal-aware fragments newly discovered during the generation.
1 code implementation • NeurIPS 2023 • Minki Kang, Seanie Lee, Jinheon Baek, Kenji Kawaguchi, Sung Ju Hwang
Large Language Models (LLMs) have shown promising performance in knowledge-intensive reasoning tasks that require a compound understanding of knowledge.
1 code implementation • 26 May 2023 • Sohyun An, Hayeon Lee, Jaehyeong Jo, Seanie Lee, Sung Ju Hwang
To tackle such limitations of existing NAS methods, we propose a paradigm shift from NAS to a novel conditional Neural Architecture Generation (NAG) framework based on diffusion models, dubbed DiffusionNAG.
1 code implementation • 12 Oct 2022 • Balhae Kim, JungWon Choi, Seanie Lee, Yoonho Lee, Jung-Woo Ha, Juho Lee
Finally, we propose a novel Bayesian pseudocoreset algorithm based on minimizing forward KL divergence.
no code implementations • 30 Sep 2022 • Seanie Lee, Minki Kang, Juho Lee, Sung Ju Hwang, Kenji Kawaguchi
Pre-training a large transformer model on a massive amount of unlabeled data and fine-tuning it on labeled datasets for diverse downstream tasks has proven to be a successful strategy, for a variety of vision and natural language processing tasks.
1 code implementation • 26 Aug 2022 • Jeffrey Willette, Seanie Lee, Bruno Andreis, Kenji Kawaguchi, Juho Lee, Sung Ju Hwang
Recent work on mini-batch consistency (MBC) for set functions has brought attention to the need for sequentially processing and aggregating chunks of a partitioned set while guaranteeing the same output for all partitions.
no code implementations • 20 May 2022 • Seanie Lee, Bruno Andreis, Kenji Kawaguchi, Juho Lee, Sung Ju Hwang
Recently, several task augmentation methods have been proposed to tackle this issue using domain-specific knowledge to design augmentation techniques to densify the meta-training task distribution.
no code implementations • ICLR 2022 • Seanie Lee, Hae Beom Lee, Juho Lee, Sung Ju Hwang
Thanks to the gradients aligned between tasks by our method, the model becomes less vulnerable to negative transfer and catastrophic forgetting.
no code implementations • 29 Sep 2021 • Andreis Bruno, Seanie Lee, A. Tuan Nguyen, Juho Lee, Eunho Yang, Sung Ju Hwang
Deep Learning algorithms are designed to operate on huge volumes of high dimensional data such as images.
1 code implementation • ACL 2021 • Seanie Lee, Minki Kang, Juho Lee, Sung Ju Hwang
QA models based on pretrained language mod-els have achieved remarkable performance on various benchmark datasets. However, QA models do not generalize well to unseen data that falls outside the training distribution, due to distributional shifts. Data augmentation (DA) techniques which drop/replace words have shown to be effective in regularizing the model from overfitting to the training data. Yet, they may adversely affect the QA tasks since they incur semantic changes that may lead to wrong answers for the QA task.
no code implementations • 11 Mar 2021 • Donggyu Kim, Seanie Lee
Since we can leverage a large amount of unlabeled data without any human supervision to train a model and transfer the knowledge to target tasks, self-supervised learning is a de-facto component for the recent success of deep learning in various fields.
1 code implementation • ICLR 2021 • Dong Bok Lee, Dongchan Min, Seanie Lee, Sung Ju Hwang
Then, the learned model can be used for downstream few-shot classification tasks, where we obtain task-specific parameters by performing semi-supervised EM on the latent representations of the support and query set, and predict labels of the query set by computing aggregated posteriors.
1 code implementation • ICLR 2021 • Seanie Lee, Dong Bok Lee, Sung Ju Hwang
In this work, we propose to mitigate the conditional text generation problem by contrasting positive pairs with negative pairs, such that the model is exposed to various valid or incorrect perturbations of the inputs, for improved generalization.
no code implementations • 25 Jun 2020 • Bruno Andreis, Seanie Lee, A. Tuan Nguyen, Juho Lee, Eunho Yang, Sung Ju Hwang
Deep models are designed to operate on huge volumes of high dimensional data such as images.
1 code implementation • ACL 2020 • Dong Bok Lee, Seanie Lee, Woo Tae Jeong, Donghwan Kim, Sung Ju Hwang
We validate our Information Maximizing Hierarchical Conditional Variational AutoEncoder (Info-HCVAE) on several benchmark datasets by evaluating the performance of the QA model (BERT-base) using only the generated QA pairs (QA-based evaluation) or by using both the generated and human-labeled pairs (semi-supervised learning) for training, against state-of-the-art baseline models.
Ranked #1 on Question Generation on Natural Questions
1 code implementation • 7 Apr 2020 • Kyubyong Park, Seanie Lee
Conversion of Chinese graphemes to phonemes (G2P) is an essential component in Mandarin Chinese Text-To-Speech (TTS) systems.
Ranked #2 on Polyphone disambiguation on CPP
1 code implementation • WS 2019 • Seanie Lee, Donggyu Kim, Jangwon Park
Adapting models to new domain without finetuning is a challenging problem in deep learning.