Kiros, Salakhutdinov and Zemel,
Department of Computer Science,
University of Toronto
Paper review for CS671A
Amlan Kar
 Neural Language Models
Distributed representation
Log-Bilinear models (Mnih & Hinton, 2007)
Log Bi-linear Model
Bias Vector
Modality Based Log Bi-linear Model (MLBL-B)
Â
Bias Vector
Factored 3-way Log Bi-linear Model (MLBL-B)
Weights determined by modality vector x
Intuition ?
Â
Problems ?
Solution ?
where,
Paper review for CS671A
Tensor Factorization ? What is F ?
Image from Kohei Hayashi's talk on Generalization of Tensor Factorization and Applications
This E can now be treated as our word embedding space !Â
This is different as it now incorporates multimodal information !
Factor Outputs - Putting in the multimodality
This is basically the dot product of the word representation vector with the image representation vector after projecting them to a Fx1 vector using the tensor factorization matrices.
We shall finally use f to generate the next word just like in the Log-Bilinear model
Â
How ?
Use each column of         Â
Â
Â
Joint Image-Text Feature Learning