DeepAI AI Chat
Log In Sign Up

A Dual Encoder Sequence to Sequence Model for Open-Domain Dialogue Modeling

by   Sharath T. S., et al.
University of California Santa Cruz

Ever since the successful application of sequence to sequence learning for neural machine translation systems, interest has surged in its applicability towards language generation in other problem domains. Recent work has investigated the use of these neural architectures towards modeling open-domain conversational dialogue, where it has been found that although these models are capable of learning a good distributional language model, dialogue coherence is still of concern. Unlike translation, conversation is much more a one-to-many mapping from utterance to a response, and it is even more pressing that the model be aware of the preceding flow of conversation. In this paper we propose to tackle this problem by introducing previous conversational context in terms of latent representations of dialogue acts over time. We inject the latent context representations into a sequence to sequence neural network in the form of dialog acts using a second encoder to enhance the quality and the coherence of the conversations generated. The main task of this research work is to show that adding latent variables that capture discourse relations does indeed result in more coherent responses when compared to conventional sequence to sequence models.


page 1

page 2

page 3

page 4


Memory-Augmented Recurrent Networks for Dialogue Coherence

Recent dialogue approaches operate by reading each word in a conversatio...

Domain Aware Neural Dialog System

We investigate the task of building a domain aware chat system which gen...

Evaluator for Emotionally Consistent Chatbots

One challenge for evaluating current sequence- or dialogue-level chatbot...

Improving a sequence-to-sequence nlp model using a reinforcement learning policy algorithm

Nowadays, the current neural network models of dialogue generation(chatb...

Discourse-Wizard: Discovering Deep Discourse Structure in your Conversation with RNNs

Spoken language understanding is one of the key factors in a dialogue sy...

Guider l'attention dans les modeles de sequence a sequence pour la prediction des actes de dialogue

The task of predicting dialog acts (DA) based on conversational dialog i...

Guiding attention in Sequence-to-sequence models for Dialogue Act prediction

The task of predicting dialog acts (DA) based on conversational dialog i...