Tree Recursive Neural Networks, Constituency Parsing, and Sentiment

Slides

• Principle of compositionality

  • The meaning(vector) of a sentence is determined by:
    • the meaning of its word
    • the rules that combine them
  • Models in this section can jointly learn parse trees and compositional vector representations

• Recursive vs. Recurrent

  • Slide 17
  • Recursive neural nets require a tree structure
  • Recursive neural nets for structure prediction
    • Inputs: two candidate children's representation
    • Outputs:
      • The semantic representation if the two nodes are merged
      • Score of how plausible the new node would be

• More complex TreeRNN units

Notes

• Recursive Neural Networks
  Vector, Matrix, Tensor for the "W"

• Constituency parsing(phrase structure parsing)

Suggested Readings

1. Constituency Parsing with a Self-Attentive Encoder
   factored self-attention

2. Parsing with Compositional Vector Grammers