A Convolutional Neural Network for Modelling Sentences

Code

• github.com/Suro-One/Hyena-Hierarchy
  pytorch★ 46
• github.com/MindSpore-scientific/code-12/tree/main/Hyena-A-Convolutional-Neural-Network-for-Modelling-Sentences
  mindspore★ 0
• github.com/Suro-One/Hyena-Hierachy
  pytorch★ 0
• github.com/gyanmittal/text-classification-using-char-level-embedding-with-cnn-and-keras
  tf★ 0
• github.com/chojc408/Dynamic-CNN-using-Global_k_MaxPooling1D
  tf★ 0
• github.com/kinimod23/ATS_Project
  tf★ 0

Abstract

The ability to accurately represent sentences is central to language understanding. We describe a convolutional architecture dubbed the Dynamic Convolutional Neural Network (DCNN) that we adopt for the semantic modelling of sentences. The network uses Dynamic k-Max Pooling, a global pooling operation over linear sequences. The network handles input sentences of varying length and induces a feature graph over the sentence that is capable of explicitly capturing short and long-range relations. The network does not rely on a parse tree and is easily applicable to any language. We test the DCNN in four experiments: small scale binary and multi-class sentiment prediction, six-way question classification and Twitter sentiment prediction by distant supervision. The network achieves excellent performance in the first three tasks and a greater than 25% error reduction in the last task with respect to the strongest baseline.

Tasks

Reproductions