Search Results for author: Geewook Kim

Found 16 papers, 9 papers with code

SCOB: Universal Text Understanding via Character-wise Supervised Contrastive Learning with Online Text Rendering for Bridging Domain Gap

no code implementations ICCV 2023 Daehee Kim, Yoonsik Kim, Donghyun Kim, Yumin Lim, Geewook Kim, Taeho Kil

In this paper, we investigate effective pre-training tasks in the broader domains and also propose a novel pre-training method called SCOB that leverages character-wise supervised contrastive learning with online text rendering to effectively pre-train document and scene text domains by bridging the domain gap.

Contrastive Learning document understanding +2

On Web-based Visual Corpus Construction for Visual Document Understanding

1 code implementation7 Nov 2022 Donghyun Kim, Teakgyu Hong, Moonbin Yim, Yoonsik Kim, Geewook Kim

In recent years, research on visual document understanding (VDU) has grown significantly, with a particular emphasis on the development of self-supervised learning methods.

document understanding Optical Character Recognition (OCR) +1

OCR-free Document Understanding Transformer

4 code implementations30 Nov 2021 Geewook Kim, Teakgyu Hong, Moonbin Yim, Jeongyeon Nam, Jinyoung Park, Jinyeong Yim, Wonseok Hwang, Sangdoo Yun, Dongyoon Han, Seunghyun Park

Current Visual Document Understanding (VDU) methods outsource the task of reading text to off-the-shelf Optical Character Recognition (OCR) engines and focus on the understanding task with the OCR outputs.

Document Image Classification document understanding +3

Revisiting Additive Compositionality: AND, OR and NOT Operations with Word Embeddings

no code implementations18 May 2021 Masahiro Naito, Sho Yokoi, Geewook Kim, Hidetoshi Shimodaira

(Q2) Ordinary additive compositionality can be seen as an AND operation of word meanings, but it is not well understood how other operations, such as OR and NOT, can be computed by the embeddings.

Word Embeddings

Cost-effective End-to-end Information Extraction for Semi-structured Document Images

no code implementations EMNLP 2021 Wonseok Hwang, Hyunji Lee, Jinyeong Yim, Geewook Kim, Minjoon Seo

A real-world information extraction (IE) system for semi-structured document images often involves a long pipeline of multiple modules, whose complexity dramatically increases its development and maintenance cost.

Stochastic Neighbor Embedding of Multimodal Relational Data for Image-Text Simultaneous Visualization

no code implementations2 May 2020 Morihiro Mizutani, Akifumi Okuno, Geewook Kim, Hidetoshi Shimodaira

Multimodal relational data analysis has become of increasing importance in recent years, for exploring across different domains of data, such as images and their text tags obtained from social networking services (e. g., Flickr).

Graph Embedding

Group-Transformer: Towards A Lightweight Character-level Language Model

no code implementations25 Sep 2019 Sungrae Park, Geewook Kim, Junyeop Lee, Junbum Cha, Ji-Hoon Kim Hwalsuk Lee

When compared to Transformers with a comparable number of parameters and time complexity, the proposed model shows better performance.

Language Modelling

Representation Learning with Weighted Inner Product for Universal Approximation of General Similarities

1 code implementation27 Feb 2019 Geewook Kim, Akifumi Okuno, Kazuki Fukui, Hidetoshi Shimodaira

In addition to the parameters of neural networks, we optimize the weights of the inner product by allowing positive and negative values.

Graph Embedding Model Selection +1

Word-like character n-gram embedding

1 code implementation WS 2018 Geewook Kim, Kazuki Fukui, Hidetoshi Shimodaira

We propose a new word embedding method called \textit{word-like character} n\textit{-gram embedding}, which learns distributed representations of words by embedding word-like character n-grams.

Segmentation Word Embeddings

Graph Embedding with Shifted Inner Product Similarity and Its Improved Approximation Capability

no code implementations4 Oct 2018 Akifumi Okuno, Geewook Kim, Hidetoshi Shimodaira

We propose shifted inner-product similarity (SIPS), which is a novel yet very simple extension of the ordinary inner-product similarity (IPS) for neural-network based graph embedding (GE).

Graph Embedding

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