Seokhwan Kim

NLP Research Scientist

San Jose

Seokhwan is currently an NLP research scientist in Adobe Research.

Prior to joining Adobe, Seokhwan conducted work in natural language understanding and spoken dialog systems where he was a Research Scientist at the Institute for Infocomm Research (I2R) in Singapore.

His PhD work focused on cross-lingual weakly-supervised language understanding at Pohang University of Science and Technology (POSTECH) in Korea, his advisor was Gary Geunbae Lee. Seokhwan also did a 5 month research internship at the Max Planck Institute for Informatics under the direction of Prof. Gerhard Weikum.

More recently, he has focused on the state tracking problems in dialog management and has contributed to the research community by co-organizing Dialog State Tracking Challenges (DSTCs).

More information can be found from his personal website.

My Publications

Learning Emphasis Selection for Written Text in Visual Media from Crowd-Sourced Label Distributions

Shirani, A., Dernoncourt, F., Asente, P., Lipka, N., Kim, S., Echevarria, J., Solorio, T. (Aug. 2, 2019)
ACL 2019

Scoring Sentence Singletons and Pairs for Abstractive Summarization

Lebanoff, L., Song, K., Dernoncourt, F., Kim, D., Kim, S., Chang, W., Liu, F. (Aug. 2, 2019)
ACL 2019

A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents

Cohan, A., Dernoncourt, F., Kim, D., Bui, T., Kim, S., Chang, W., Goharian, N. (Jun. 1, 2018)
Proceedings of NAACL-HLT 2018

PhotoshopQuiA: A Corpus of Non-Factoid Questions and Answers for Why-Question Answering

Dulceanu, A., Le Dinh, T., Chang, W., Bui, T., Kim, D., Vu, M., Kim, S. (May. 7, 2018)
Proc. of LREC 2018