TY - GEN
T1 - Value-Wise ConvNet for Transformer Models
T2 - 40th IEEE International Conference on Data Engineering, ICDE 2024
AU - Saaki, Mohsen
AU - Hosseini, Saeid
AU - Rahmani, Sana
AU - Kangavari, Mohammad Reza
AU - Hua, Wen
AU - Zhou, X.
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - Addressing the challenge of matching queries with the right experts amid temporal-textual inconsistencies, we present a novel approach that combines an attention-based text embedding model with a continuous-time module. This method effectively maps queries to relevant experts by analyzing concept-oriented vectors and user behavior, demonstrating significant effectiveness on StackOverflow and Yahoo datasets.
AB - Addressing the challenge of matching queries with the right experts amid temporal-textual inconsistencies, we present a novel approach that combines an attention-based text embedding model with a continuous-time module. This method effectively maps queries to relevant experts by analyzing concept-oriented vectors and user behavior, demonstrating significant effectiveness on StackOverflow and Yahoo datasets.
KW - context-wise transformers
KW - online expert recommendation
KW - time-aware embedding
KW - user behavioral patterns
UR - http://www.scopus.com/inward/record.url?scp=85200450051&partnerID=8YFLogxK
U2 - 10.1109/ICDE60146.2024.00489
DO - 10.1109/ICDE60146.2024.00489
M3 - Conference article published in proceeding or book
AN - SCOPUS:85200450051
T3 - Proceedings - International Conference on Data Engineering
SP - 5715
EP - 5716
BT - Proceedings - 2024 IEEE 40th International Conference on Data Engineering, ICDE 2024
PB - IEEE Computer Society
Y2 - 13 May 2024 through 17 May 2024
ER -