File:2014 ALatentSemanticModelwithConvolu Fig1.png

Summary

Figure 1: The CLSM maps a variable-length word sequence to a low-dimensional vector in a latent semantic space. A word contextual window size (i.e. the receptive field) of three is used in the illustration. Convolution over word sequence via learned matrix WC is performed implicitly via the earlier layer’s mapping with a local receptive field. The dimensionalities of the convolutional layer and the semantic layer are set to 300 and 128 in the illustration, respectively. The max operation across the sequence is applied for each of 300 feature dimensions separately. (Only the first dimension is shown to avoid figure clutter.) In: Shen et al. (2014)