A Convolutional Neural Network for Modelling Sentences

Journal article

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, capable of explicitly capturing short and long-range relations. The net...

Expand abstract

Authors: Kalchbrenner, N; Grefenstette, E; Blunsom, P

• Journal: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics
• Publication date: 2014-06-01