Deep Structured Semantic Model (DSSM) Algorithm

A Deep Structured Semantic Model (DSSM) Algorithm is a Neural Semantic Indexing Algorithm that is based on a Deep Neural Network Training Algorithm.

• Context:
  • It was first developed by Huang et al. (2013).
  • It can be implemented by a DSSM System to solve a DSSM Task.
• Example(s):
  • …
• Counter-Example(s):
  • Convolutional Latent Semantic Model (CLSM) Algorithm (Shen et al., 2014),
  • a Hierarchical CNN-based Semantic Indexing Framework Algorithm (Yan et al., 2016).
• See: Deep Learning Neural Network, Deep Learning System Semantic Analysis, Vectorial Semantics, Artificial Neural Network, Synonymy, Polysemy, Word Hashing, Neural Natural Language Processing System.

---

---

References

2013

• (Huang et al., 2013) ⇒ Po-Sen Huang, Xiaodong He, Jianfeng Gao, Li Deng, Alex Acero, and Larry Heck. (2013). “Learning Deep Structured Semantic Models for Web Search Using Clickthrough Data.” In: Proceedings of the 22nd ACM International Conference on Conference on information & knowledge management. ISBN:978-1-4503-2263-8 doi:10.1145/2505515.2505665
  • QUOTE: The typical DNN architecture we have developed for mapping the raw text features into the features in a semantic space is shown in Fig. 1. The input (raw text features) to the DNN is a highdimensional term vector, e.g., raw counts of terms in a query or a document without normalization, and the output of the DNN is a concept vector in a low-dimensional semantic feature space.
    
    Figure 1: Illustration of the DSSM. It uses a DNN to map high-dimensional sparse text features into low-dimensional dense features in a semantic space. The first hidden layer, with 30k units, accomplishes word hashing. The word-hashed features are then projected through multiple layers of non-linear projections. The final layer’s neural activities in this DNN form the feature in the semantic space.

---