Paper: Recurrent Convolutional Neural Networks for Discourse Compositionality

ACL ID W13-3214
Title Recurrent Convolutional Neural Networks for Discourse Compositionality
Venue Continuous Vector Space Models and their Compositionality
Session
Year 2013
Authors

The compositionality of meaning extends beyond the single sentence. Just as words combine to form the meaning of sen- tences, so do sentences combine to form the meaning of paragraphs, dialogues and general discourse. We introduce both a sentence model and a discourse model cor- responding to the two levels of composi- tionality. The sentence model adopts con- volution as the central operation for com- posing semantic vectors and is based on a novel hierarchical convolutional neural network. The discourse model extends the sentence model and is based on a recur- rent neural network that is conditioned in a novel way both on the current sentence and on the current speaker. The discourse model is able to capture both the sequen- tiality of sentences and the interaction be- tween different sp...