Search Results for author: Minsoo Khang

Found 5 papers, 2 papers with code

KIEval: Evaluation Metric for Document Key Information Extraction

no code implementations7 Mar 2025 Minsoo Khang, Sang Chul Jung, Sungrae Park, Teakgyu Hong

Evaluation of structured information provides assessment of Document KIE models that are more reflective of extracting grouped information from documents in industrial settings.

Key Information Extraction

System Message Generation for User Preferences using Open-Source Models

no code implementations17 Feb 2025 Minbyul Jeong, Jungho Cho, Minsoo Khang, Dawoon Jung, Teakgyu Hong

System messages play a crucial role in interactions with large language models (LLMs), often serving as prompts to initiate conversations.

TFLOP: Table Structure Recognition Framework with Layout Pointer Mechanism

1 code implementation21 Jan 2025 Minsoo Khang, Teakgyu Hong

Table Structure Recognition (TSR) is a task aimed at converting table images into a machine-readable format (e. g. HTML), to facilitate other applications such as information retrieval.

Information Retrieval

Model-Based Data-Centric AI: Bridging the Divide Between Academic Ideals and Industrial Pragmatism

no code implementations4 Mar 2024 Chanjun Park, Minsoo Khang, Dahyun Kim

This paper delves into the contrasting roles of data within academic and industrial spheres, highlighting the divergence between Data-Centric AI and Model-Agnostic AI approaches.

SRFormer: Text Detection Transformer with Incorporated Segmentation and Regression

2 code implementations21 Aug 2023 Qingwen Bu, Sungrae Park, Minsoo Khang, Yichuan Cheng

In light of this, we constrain the incorporation of segmentation branches to the first few decoder layers and employ progressive regression refinement in subsequent layers, achieving performance gains while minimizing computational load from the mask. Furthermore, we propose a Mask-informed Query Enhancement module.

Decoder regression +3

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