CLSep 22, 2020

Controlling Style in Generated Dialogue

arXiv:2009.10855v156 citations
Originality Synthesis-oriented
AI Analysis

This work addresses the challenge of making large conversational models more consistent and controllable for users, though it is incremental as it adapts existing methods to a new domain.

The authors tackled the problem of controlling style in open-domain dialogue generation by adapting three existing controllable generation architectures to match one of about 200 styles, comparing their performance and trade-offs to enable varied styled conversation replies.

Open-domain conversation models have become good at generating natural-sounding dialogue, using very large architectures with billions of trainable parameters. The vast training data required to train these architectures aggregates many different styles, tones, and qualities. Using that data to train a single model makes it difficult to use the model as a consistent conversational agent, e.g. with a stable set of persona traits and a typical style of expression. Several architectures affording control mechanisms over generation architectures have been proposed, each with different trade-offs. However, it remains unclear whether their use in dialogue is viable, and what the trade-offs look like with the most recent state-of-the-art conversational architectures. In this work, we adapt three previously proposed controllable generation architectures to open-domain dialogue generation, controlling the style of the generation to match one among about 200 possible styles. We compare their respective performance and tradeoffs, and show how they can be used to provide insights into existing conversational datasets, and generate a varied set of styled conversation replies.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes