Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Bang, Jeesoo"'
Despite advancements in on-topic dialogue systems, effectively managing topic shifts within dialogues remains a persistent challenge, largely attributed to the limited availability of training datasets. To address this issue, we propose Multi-Passage
Externí odkaz:
http://arxiv.org/abs/2403.05814
To address the data scarcity issue in Conversational question answering (ConvQA), a dialog inpainting method, which utilizes documents to generate ConvQA datasets, has been proposed. However, the original dialog inpainting model is trained solely on
Externí odkaz:
http://arxiv.org/abs/2311.07589
Publikováno v:
In Pattern Recognition Letters December 2020 140:230-237
Publikováno v:
2015 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU); 1/1/2015, p771-776, 6p
Autor:
Choi, Junhwi, Ryu, Seonghan, Lee, Kyusong, Kim, Yonghee, Koo, Sangjun, Bang, Jeesoo, Park, Seonyeong, Lee, Gary Geunbae
Publikováno v:
Multimodal Analyses enabling Artificial Agents in Human-Machine Interaction; 2015, p69-77, 9p
Publikováno v:
Multimodal Analyses enabling Artificial Agents in Human-Machine Interaction; 2015, p78-87, 10p
Publikováno v:
2015 International Conference on Big Data & Smart Computing (BIGCOMP); 2015, p238-243, 6p
Publikováno v:
2014 IEEE International Conference on Acoustics, Speech & Signal Processing (ICASSP); 2014, p935-939, 5p
Publikováno v:
ACM Transactions on Asian Language Information Processing; Dec2014, Vol. 13 Issue 4, p1-21, 21p