This paper presents a novel latent variable recurrent neural network architecture for jointly modeling sequences of words and (possibly latent) discourse relations between adjacent sentences.
DIALOG ACT CLASSIFICATION IMPLICIT DISCOURSE RELATION CLASSIFICATION LANGUAGE MODELLING
The identification of Dialogue Act’s (DA) is an important aspect in determining the meaning of an utterance for many applications that require natural language understanding, and recent work using recurrent neural networks (RNN) has shown promising results when applied to the DA classification problem.
DIALOG ACT CLASSIFICATION DIALOGUE ACT CLASSIFICATION NATURAL LANGUAGE UNDERSTANDING WORD EMBEDDINGS
Deep neural networks reach state-of-the-art performance for wide range of natural language processing, computer vision and speech applications.
Ranked #1 on
Dialogue Act Classification
on Switchboard corpus
DIALOG ACT CLASSIFICATION DIALOGUE ACT CLASSIFICATION TEXT CLASSIFICATION WORD EMBEDDINGS
Therefore it is a useful technique for tuning ANN models to yield the best performances for natural language processing tasks.