Learning to rank for spoken content transcriptions /
Farida Mohamed Sabry
Learning to rank for spoken content transcriptions / التعلم الى لتصنيف نتائج بحث المحتوى المنطوق Farida Mohamed Sabry ; Supervised Nevin Darwish , Mayada Hadhoud - Cairo : Farida Mohamed Sabry , 2018 - 70 P. : charts ; 30cm
Thesis (Ph.D.) - Cairo University - Faculty of Engineering - Department of Computer Engineering
This thesis addresses the problem of ranking of spoken content retrieval (SCR). It shows the effectiveness of applying learning to rank techniques for the ranking of transcriptions based on features extracted from the metadata and the timed spoken content transcription with respect to one of the base- line unsupervised traditional scoring. Algorithms for reduction and bagging of features are implemented that outperform the state-of-art algorithms
Learning to rank Spoken content retrieval Spoken transcriptions
Learning to rank for spoken content transcriptions / التعلم الى لتصنيف نتائج بحث المحتوى المنطوق Farida Mohamed Sabry ; Supervised Nevin Darwish , Mayada Hadhoud - Cairo : Farida Mohamed Sabry , 2018 - 70 P. : charts ; 30cm
Thesis (Ph.D.) - Cairo University - Faculty of Engineering - Department of Computer Engineering
This thesis addresses the problem of ranking of spoken content retrieval (SCR). It shows the effectiveness of applying learning to rank techniques for the ranking of transcriptions based on features extracted from the metadata and the timed spoken content transcription with respect to one of the base- line unsupervised traditional scoring. Algorithms for reduction and bagging of features are implemented that outperform the state-of-art algorithms
Learning to rank Spoken content retrieval Spoken transcriptions