Ho-Jin Seo

About

Ho-Jin Seo is a leading researcher at the intersection of natural language processing (NLP) and enterprise automation, with a focus on deep learning-based conversational AI and robotic process automation (RPA). His most impactful work centers on advancing neural question generation (NQG) for chatbot development, notably through the "Ensemble-NQG-T5" model, which leverages the Text-to-Text Transfer Transformer to augment training datasets—a critical innovation that has garnered 21 citations. Seo also pioneered "KoRASA," a pipeline optimization for open-source Korean NLP frameworks, addressing scalability challenges in multilingual chatbot systems (11 citations). Beyond NLP, he developed "EnterRPA," an open-source RPA framework designed to mitigate failure risks in enterprise automation, earning 4 citations. Seo’s contributions are particularly notable for tackling real-world deployment hurdles, such as data scarcity in deep learning and the functional limitations of domain-specific chatbots. His work has been recognized for bridging cutting-edge AI techniques with practical, industry-ready solutions, making him a key figure in both academic and applied research communities.

Research Focus

Key Achievements

Top Papers

1. 1
   Ensemble-NQG-T5: Ensemble Neural Question Generation Model Based on Text-to-Text Transfer Transformer

   21 citations · 2023
2. 2
   KoRASA: Pipeline Optimization for Open-Source Korean Natural Language Understanding Framework Based on Deep Learning

   11 citations · 2021
3. 3
   EnterRPA: Open-Source Robotic Process Automation for Enterprise

   4 citations · 2023

Key Collaborators

Contact & Links