Convolutional Semantic Similarity Network Entity Linking System

A Convolutional Semantic Similarity Network Entity Linking System is an Entity Linking System that can detect entities in a text document and create links between them by training a Convolutional Semantic Similarity Neural Network.

• AKA: CNN-SSN Entity Linking System.
• Example(s):
  • Francis-Landau et al. (2016) entity linking system,
  • …
• Counter-Example(s):
  • a Deep Similarity Neural Network QA System,
  • a Gene Semantic Similarity Disease Phenotype Detection System,
  • a Neural Transformer-based Network Training System,
  • a Neural Sequence-to-Sequence (seq2seq)-based Model Training System.
• See: Semantic Similarity Measure, Taxonomy, Directed Graph, Semantic Word Similarity, Semantic Word Similarity Benchmark Task.

---

---

References

2016

• (Francis-Landau et al., 2016) ⇒ Matthew Francis-Landau, Greg Durrett, and Dan Klein. (2016). “Capturing Semantic Similarity for Entity Linking with Convolutional Neural Networks.” In: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2016).
  • QUOTE: Our model focuses on two core ideas: first, that topic semantics at different granularities in a document are helpful in determining the genres of entities for entity linking, and second, that CNNs can distill a block of text into a meaningful topic vector.

    (...) As shown in the middle of Figure 1, each feature in $f_C$ is a cosine similarity between a topic vector associated with the source document and a topic vector associated with the target entity. These vectors are computed by distinct CNNs operating over different subsets of relevant text.

Figure 1: Extraction of convolutional vector space features $f_C\left (x, t_e\right)$. Three types of information from the input document and two types of information from the proposed title are fed through convolutional networks to produce vectors, which are systematically compared with cosine similarity to derive real-valued semantic similarity features.

---