A Deep Ensemble Model with Slot Alignment for Sequence-to-Sequence Natural Language Generation

05/16/2018
by   Juraj Juraska, et al.
0

Natural language generation lies at the core of generative dialogue systems and conversational agents. We describe an ensemble neural language generator, and present several novel methods for data representation and augmentation that yield improved results in our model. We test the model on three datasets in the restaurant, TV and laptop domains, and report both objective and subjective evaluations of our best model. Using a range of automatic metrics, as well as human evaluators, we show that our approach achieves better results than state-of-the-art models on the same datasets.

READ FULL TEXT
research
08/25/2016

A Context-aware Natural Language Generator for Dialogue Systems

We present a novel natural language generation system for spoken dialogu...
research
10/25/2019

Measuring Conversational Fluidity in Automated Dialogue Agents

We present an automated evaluation method to measure fluidity in convers...
research
06/17/2016

Sequence-to-Sequence Generation for Spoken Dialogue via Deep Syntax Trees and Strings

We present a natural language generator based on the sequence-to-sequenc...
research
06/11/2016

Natural Language Generation in Dialogue using Lexicalized and Delexicalized Data

Natural language generation plays a critical role in spoken dialogue sys...
research
04/12/2021

Estimating Subjective Crowd-Evaluations as an Additional Objective to Improve Natural Language Generation

Human ratings are one of the most prevalent methods to evaluate the perf...
research
07/08/2019

Multiple Generative Models Ensemble for Knowledge-Driven Proactive Human-Computer Dialogue Agent

Multiple sequence to sequence models were used to establish an end-to-en...
research
06/16/2022

DialogueScript: Using Dialogue Agents to Produce a Script

We present a novel approach to generating scripts by using agents with d...

Please sign up or login with your details

Forgot password? Click here to reset