Published on Wed May 16 2018

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

Juraj Juraska, Panagiotis Karagiannis, Kevin K. Bowden, Marilyn A. Walker

We describe an ensemble neural language generator. We test the model on three datasets in the restaurant, TV and laptop domains. We show that our approach achieves better results than state-of-the-art models.

0
0
0
Abstract

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.

Sun Jun 02 2019
NLP
A Survey of Natural Language Generation Techniques with a Focus on Dialogue Systems - Past, Present and Future Directions
Natural Language Generation (NLG) is a growing field of research in artificial intelligence. NLG aims to automatically generate language that is coherent and understandable to humans. We provide a comprehensive review of approaches to building dialogue systems.
0
0
0
Fri Nov 18 2016
Neural Networks
Generative Deep Neural Networks for Dialogue: A Short Review
Deep neural networks have shown promising results for unstructured tasks, such as word-level dialogue response generation. The hope is that such models will be able to leverage massive amounts of data.
0
0
0
Sat Jun 11 2016
NLP
Natural Language Generation in Dialogue using Lexicalized and Delexicalized Data
We present a new approach to natural language generation for task-oriented dialogue using recurrent neural networks in an encoder-decoder framework. Our model uses both lexicalized and delexicalized components i.e. slot-value pairs for dialogue acts.
0
0
0
Tue Oct 02 2018
NLP
Findings of the E2E NLG Challenge
This paper summarises the experimental setup and results of the first shared task on end-to-end (E2E) natural language generation (NLG) in spoken dialogue. We compare 62 systems submitted by 17 institutions, covering a wide range of approaches, including machine learning.
0
0
0
Fri Jun 12 2020
Artificial Intelligence
A Generative Model for Joint Natural Language Understanding and Generation
Natural language understanding (NLU) and natural language generation (NLG) are two fundamental and related tasks in building task-oriented dialogue systems. NLU tackles the transformation from natural language to formal representations, whereas NLG does the reverse. A key to success in either task is parallel training
0
0
0
Thu Jun 01 2017
NLP
Natural Language Generation for Spoken Dialogue System using RNN Encoder-Decoder Networks
Natural language generation (NLG) is a critical component in a spoken conversations. This paper presents a Recurrent Neural Network based on an LSTM-based decoder. The proposed model was extensively evaluated on four different NLG datasets.
0
0
0