Learning from Mistakes: Combining Ontologies via Self-Training for Dialogue Generation

by   Lena Reed, et al.

Natural language generators (NLGs) for task-oriented dialogue typically take a meaning representation (MR) as input. They are trained end-to-end with a corpus of MR/utterance pairs, where the MRs cover a specific set of dialogue acts and domain attributes. Creation of such datasets is labor-intensive and time-consuming. Therefore, dialogue systems for new domain ontologies would benefit from using data for pre-existing ontologies. Here we explore, for the first time, whether it is possible to train an NLG for a new larger ontology using existing training sets for the restaurant domain, where each set is based on a different ontology. We create a new, larger combined ontology, and then train an NLG to produce utterances covering it. For example, if one dataset has attributes for family-friendly and rating information, and the other has attributes for decor and service, our aim is an NLG for the combined ontology that can produce utterances that realize values for family-friendly, rating, decor and service. Initial experiments with a baseline neural sequence-to-sequence model show that this task is surprisingly challenging. We then develop a novel self-training method that identifies (errorful) model outputs, automatically constructs a corrected MR input to form a new (MR, utterance) training pair, and then repeatedly adds these new instances back into the training data. We then test the resulting model on a new test set. The result is a self-trained model whose performance is an absolute 75.4 improvement over the baseline model. We also report a human qualitative evaluation of the final model showing that it achieves high naturalness, semantic coherence and grammaticality


page 1

page 2

page 3

page 4


Controlling Personality-Based Stylistic Variation with Neural Natural Language Generators

Natural language generators for task-oriented dialogue must effectively ...

Sequence-to-Sequence Data Augmentation for Dialogue Language Understanding

In this paper, we study the problem of data augmentation for language un...

Stochastic Natural Language Generation Using Dependency Information

This article presents a stochastic corpus-based model for generating nat...

A Good Sample is Hard to Find: Noise Injection Sampling and Self-Training for Neural Language Generation Models

Deep neural networks (DNN) are quickly becoming the de facto standard mo...

Controllable Generation of Dialogue Acts for Dialogue Systems via Few-Shot Response Generation and Ranking

Dialogue systems need to produce responses that realize multiple types o...

Characterizing Variation in Crowd-Sourced Data for Training Neural Language Generators to Produce Stylistically Varied Outputs

One of the biggest challenges of end-to-end language generation from mea...

Jurassic is (almost) All You Need: Few-Shot Meaning-to-Text Generation for Open-Domain Dialogue

One challenge with open-domain dialogue systems is the need to produce h...

Please sign up or login with your details

Forgot password? Click here to reset