Doo Soon Kim is a senior research engineer at Adobe Research. Doo Soon’s research interests include Natural Language Processing, Machine Learning, Semantic technologies and Artificial Intelligence. He received his PhD from University of Texas at Austin where he was a core researcher in high-profile projects such as Vulcan’s (current AI2) Halo Project and DARPA’s Machine Reading project. After the PhD, he was a researcher at Accenture Technology Lab and Bosch Research, working on a wide range of NLP projects such as Information Extraction, Question Answering, and Document Summarization.

For more information, please visit his personal homepage.

Publications

TutorialVQA: Question Answering Dataset for Tutorial Videos

Colas, A., Kim, S., Dernoncourt, F., Gupte, S., Wang, Z., Kim, D. (May. 12, 2020)

LREC 2020

Propagate-Selector: Detecting Supporting Sentences for Question Answering via Graph Neural Networks

Yoon, S., Dernoncourt, F., Kim, D., Bui, T., Jung, K. (May. 12, 2020)

LREC 2020

DSTC8-AVSD: Multimodal Semantic Transformer Network with Retrieval Style Word Generator

Yoon, S., Lee, H., Dernoncourt, F., Kim, D., Bui, T., Jung, K. (Feb. 8, 2020)

AAAI 2020 Dialog System Technology Challenge (DSTC8)

Analyzing Sentence Fusion in Abstractive Summarization

Lebanoff, L., Muchovej, J., Dernoncourt, F., Kim, D., Kim, S., Chang, W., Liu, F. (Nov. 4, 2019)

EMNLP 2019 Summarization Workshop