SideControl: Controlled Open-domain Dialogue Generation via Additive Side Networks

by   Wanyu Du, et al.

Transformer-based pre-trained language models boost the performance of open-domain dialogue systems. Prior works leverage Transformer-based pre-trained language models to generate texts with desired attributes in two general approaches: (1) gradient-based methods: updating all latent representations of pre-trained models with gradients from attribute models; (2) weighted-decoding methods: re-ranking beam candidates from pre-trained models with attribute functions. However, gradient-based methods lead to high computation cost and can easily get overfitted on small training sets, while weighted-decoding methods are inherently constrained by the low-variance high-bias pre-trained model. In this work, we propose a novel approach to control the generation of Transformer-based pre-trained language models: the SideControl framework, which leverages a novel control attributes loss to incorporate useful control signals, and is shown to perform well with very limited training samples. We evaluate our proposed method on two benchmark open-domain dialogue datasets, and results show that the SideControl framework has better controllability, higher generation quality and better sample-efficiency than existing gradient-based and weighted-decoding baselines.



There are no comments yet.


page 1

page 2

page 3

page 4


Are Pre-trained Language Models Knowledgeable to Ground Open Domain Dialogues?

We study knowledge-grounded dialogue generation with pre-trained languag...

Response Generation with Context-Aware Prompt Learning

Pre-trained language models (PLM) have marked a huge leap in neural dial...

Open-Domain Dialogue Generation Based on Pre-trained Language Models

Pre-trained language models have been successfully used in response gene...

Does the Objective Matter? Comparing Training Objectives for Pronoun Resolution

Hard cases of pronoun resolution have been used as a long-standing bench...

Detect and Perturb: Neutral Rewriting of Biased and Sensitive Text via Gradient-based Decoding

Written language carries explicit and implicit biases that can distract ...

StyleDGPT: Stylized Response Generation with Pre-trained Language Models

Generating responses following a desired style has great potentials to e...

Identifying Untrustworthy Samples: Data Filtering for Open-domain Dialogues with Bayesian Optimization

Being able to reply with a related, fluent, and informative response is ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.