Search Results for author: Ho-Jin Choi

Found 19 papers, 6 papers with code

PERSONACHATGEN: Generating Personalized Dialogues using GPT-3

1 code implementation CCGPK (COLING) 2022 Young-Jun Lee, Chae-Gyun Lim, Yunsu Choi, Ji-Hui Lm, Ho-Jin Choi

However, since this dataset is frozen in 2018, the dialogue agents trained on this dataset would not know how to interact with a human who loves “Wandavision.” One way to alleviate this problem is to create a large-scale dataset.

Sentence

Does GPT-3 Generate Empathetic Dialogues? A Novel In-Context Example Selection Method and Automatic Evaluation Metric for Empathetic Dialogue Generation

1 code implementation COLING 2022 Young-Jun Lee, Chae-Gyun Lim, Ho-Jin Choi

Although several studies have investigated few-shot in-context learning for empathetic dialogue generation, an in-depth analysis of the generation of empathetic dialogue with in-context learning remains unclear, especially in GPT-3 (Brown et al., 2020).

Dialogue Generation In-Context Learning

Large Language Models can Share Images, Too!

1 code implementation23 Oct 2023 Young-Jun Lee, Jonghwan Hyeon, Ho-Jin Choi

To our knowledge, this is the first study to assess the image-sharing ability of LLMs in a zero-shot setting without visual foundation models.

Leveraging Image Augmentation for Object Manipulation: Towards Interpretable Controllability in Object-Centric Learning

no code implementations13 Oct 2023 Jinwoo Kim, Janghyuk Choi, Jaehyun Kang, Changyeon Lee, Ho-Jin Choi, Seon Joo Kim

The binding problem in artificial neural networks is actively explored with the goal of achieving human-level recognition skills through the comprehension of the world in terms of symbol-like entities.

Image Augmentation Object

Shepherding Slots to Objects: Towards Stable and Robust Object-Centric Learning

1 code implementation CVPR 2023 Jinwoo Kim, Janghyuk Choi, Ho-Jin Choi, Seon Joo Kim

Object-centric learning (OCL) aspires general and compositional understanding of scenes by representing a scene as a collection of object-centric representations.

Object

DialogCC: Large-Scale Multi-Modal Dialogue Dataset

no code implementations8 Dec 2022 Young-Jun Lee, Byungsoo Ko, Han-Gyu Kim, Ho-Jin Choi

As sharing images in an instant message is a crucial factor, there has been active research on learning a image-text multi-modal dialogue model.

Retrieval Text Retrieval

Pneg: Prompt-based Negative Response Generation for Dialogue Response Selection Task

no code implementations31 Oct 2022 Nyoungwoo Lee, ChaeHun Park, Ho-Jin Choi, Jaegul Choo

To overcome these limitations, this paper proposes a simple but efficient method for generating adversarial negative responses leveraging a large-scale language model.

Language Modelling Response Generation +1

AltUB: Alternating Training Method to Update Base Distribution of Normalizing Flow for Anomaly Detection

no code implementations26 Oct 2022 Yeongmin Kim, Huiwon Jang, DongKeon Lee, Ho-Jin Choi

To break through these observations, we propose a simple solution AltUB which introduces alternating training to update the base distribution of normalizing flow for anomaly detection.

Ranked #2 on Anomaly Detection on BTAD (using extra training data)

Unsupervised Anomaly Detection

Evaluating Predictive Uncertainty under Distributional Shift on Dialogue Dataset

no code implementations1 Sep 2021 Nyoungwoo Lee, ChaeHun Park, Ho-Jin Choi

In open-domain dialogues, predictive uncertainties are mainly evaluated in a domain shift setting to cope with out-of-distribution inputs.

Dissecting Catastrophic Forgetting in Continual Learning by Deep Visualization

1 code implementation6 Jan 2020 Giang Nguyen, Shuan Chen, Thao Do, Tae Joon Jun, Ho-Jin Choi, Daeyoung Kim

Interpreting the behaviors of Deep Neural Networks (usually considered as a black box) is critical especially when they are now being widely adopted over diverse aspects of human life.

Continual Learning

Korean TimeML and Korean TimeBank

no code implementations LREC 2016 Young-Seob Jeong, Won-Tae Joo, Hyun-Woo Do, Chae-Gyun Lim, Key-Sun Choi, Ho-Jin Choi

Before developing the system, it first necessary to define or design the structure of temporal information.

Cannot find the paper you are looking for? You can Submit a new open access paper.