The research team led by Professor Kyo-Min Jung from the Department of Electrical and Computer Engineering at Seoul National University (Ph.D. candidate Ju Sung-ho*, Ph.D. candidate Lee Kang-il*, master’s Candidate Min Kyung-min*, *: equal contributions) has been awarded the Best Paper Award in the Task-oriented Conversational Modeling with Subjective Knowledge track of the 11th Dialogue System Technology Challenge (DSTC11), a renowned international competition in the field of conversational systems. The research was carried out in collaboration with LG AI Research.
During the DSTC workshop, a total of five tracks were held, and for each track, the best paper was selected based on the excellence of the papers and the performance of the evaluated models in the challenge.
The award-winning paper, "Leveraging Ensemble Techniques and Metadata for Subjective Knowledge-grounded Conversational Systems," proposed the utilization of ensemble techniques based on metadata from dialogue datasets, demonstrating exceptional performance in conversational systems. Particularly, it achieved the top position in the accuracy category of dialogues.
This paper is scheduled to be presented at the SIGDAL workshop, which will be held in Czech Republic in September 2023.
Translated by: Do-Hyung Kim, English Editor of the Department of Electrical and Computer Engineering, email@example.com