In this section, we present our annotation-based probabilistic latent semantic analysis algorithm (aPLSA), which extends the traditional PLSA model by incorporating annotated auxiliary image data.

3.1 Probabilistic Latent Semantic Analysis

To formally introduce the aPLSA model, we start from the probabilistic latent semantic analysis (PLSA) (Hofmann, 1999) model.

What we need to do is to uncover this latent semantic information by finding out what is common among them.

Probabilistic latent semantic analysis (PLSA) is a widely used probabilistic model (Hofmann, 1999), and could be considered as a probabilistic implementation of latent semantic analysis (L SA) (Deerwester et al., 1990).

We are currently exploring the infinite latent semantic feature model (ILFM; Griffiths & Ghahramani, 2005), which assumes a nonparametric Indian Buffet prior to the binary feature vector and models neural activation with a linear Gaussian model.

We are investigating if the compositional models also operate in the learned latent semantic space.

There are also efforts to recover the latent semantic structure from text corpora using techniques such as LSA (Landauer & Dumais, 1997) and topic models (Blei et al., 2003).

Statistical measures of associations between terms include estimations by the co-occurrence in the whole collection, such as Point-wise Mutual Information (PMI) and Latent Semantic Analysis (LSA).

Latent Semantic Analysis (LSA) (Landauer and Dumais, 1997) creates a semantic space from a collection of documents to measure the semantic relatedness of words.

For LSA, we used the online demonstration mode from the Latent Semantic Analysis page from the University of Colorado at Boulder.3 For PMI, we used the online API provided by the CogWorks Lab at the Rensselaer Polytechnic Institute.4