Context Matters in Semantically Controlled Language Generation for Task-oriented Dialogue Systems

TL;DR

This paper explores how incorporating dialogue history and immediate context improves the quality and variety of responses in task-oriented dialogue systems, using pre-trained models and a re-ranking approach.

Contribution

It introduces a contextual language generation framework combining pre-trained models with immediate context, enhancing response diversity and accuracy in task-oriented dialogues.

Findings

Pre-trained context models improve response quality.

Immediate preceding user utterance is crucial for context.

Re-ranking significantly boosts automatic metric scores.

Abstract

This work combines information about the dialogue history encoded by pre-trained model with a meaning representation of the current system utterance to realize contextual language generation in task-oriented dialogues. We utilize the pre-trained multi-context ConveRT model for context representation in a model trained from scratch; and leverage the immediate preceding user utterance for context generation in a model adapted from the pre-trained GPT-2. Both experiments with the MultiWOZ dataset show that contextual information encoded by pre-trained model improves the performance of response generation both in automatic metrics and human evaluation. Our presented contextual generator enables higher variety of generated responses that fit better to the ongoing dialogue. Analysing the context size shows that longer context does not automatically lead to better performance, but the immediate preceding user utterance plays an essential role for contextual generation. In addition, we also propose a re-ranker for the GPT-based generation model. The experiments show that the response selected by the re-ranker has a significant improvement on automatic metrics.