Search Results for author: Sungzoon Cho

Found 11 papers, 3 papers with code

Pretraining Vision-Language Model for Difference Visual Question Answering in Longitudinal Chest X-rays

no code implementations14 Feb 2024 Yeongjae Cho, Taehee Kim, Heejun Shin, Sungzoon Cho, Dongmyung Shin

The model is developed using a step-by-step approach, starting with being pretrained on natural images and texts, followed by being trained using longitudinal chest X-ray data.

Language Modelling Question Answering +1

MEMTO: Memory-guided Transformer for Multivariate Time Series Anomaly Detection

1 code implementation NeurIPS 2023 Junho Song, Keonwoo Kim, Jeonglyul Oh, Sungzoon Cho

It is designed to incorporate a novel memory module that can learn the degree to which each memory item should be updated in response to the input data.

Anomaly Detection Time Series +1

Named Entity Normalization Model Using Edge Weight Updating Neural Network: Assimilation Between Knowledge-Driven Graph and Data-Driven Graph

no code implementations14 Jun 2021 Sung Hwan Jeon, Sungzoon Cho

More precise named entity normalization in text mining will benefit other subsequent text analytic applications.

Domain-slot Relationship Modeling using a Pre-trained Language Encoder for Multi-Domain Dialogue State Tracking

no code implementations1 Jan 2021 Jinwon An, Misuk Kim, Sungzoon Cho, Junseong Bang

We propose a model for multi-domain dialogue state tracking that effectively models the relationship among domain-slot pairs using a pre-trained language encoder.

Dialogue State Tracking Language Modelling +1

SARN: Relational Reasoning through Sequential Attention

no code implementations1 Nov 2018 Jinwon An, Sungwon Lyu, Sungzoon Cho

This paper proposes an attention module augmented relational network called SARN(Sequential Attention Relational Network) that can carry out relational reasoning by extracting reference objects and making efficient pairing between objects.

Relational Reasoning

CRAM: Clued Recurrent Attention Model

no code implementations28 Apr 2018 Minki Chung, Sungzoon Cho

To overcome the poor scalability of convolutional neural network, recurrent attention model(RAM) selectively choose what and where to look on the image.

Image Classification

Finding ReMO (Related Memory Object): A Simple Neural Architecture for Text based Reasoning

no code implementations ICLR 2018 Jihyung Moon, Hyochang Yang, Sungzoon Cho

To solve the text-based question and answering task that requires relational reasoning, it is necessary to memorize a large amount of information and find out the question relevant information from the memory.

Ranked #4 on Question Answering on bAbi (Mean Error Rate metric)

Question Answering Relation +2

Squeezed Convolutional Variational AutoEncoder for Unsupervised Anomaly Detection in Edge Device Industrial Internet of Things

no code implementations18 Dec 2017 Dohyung Kim, Hyochang Yang, Minki Chung, Sungzoon Cho

In this paper, we propose Squeezed Convolutional Variational AutoEncoder (SCVAE) for anomaly detection in time series data for Edge Computing in Industrial Internet of Things (IIoT).

Edge-computing Time Series +2

Distance-based Self-Attention Network for Natural Language Inference

no code implementations6 Dec 2017 Jinbae Im, Sungzoon Cho

Motivated by the Transformer, Directional Self Attention Network (Shen et al., 2017), a fully attention-based sentence encoder, was proposed.

Machine Translation Natural Language Inference +2

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