Prompting for a conversation: How to control a dialog model?

09/22/2022
by   Josef Valvoda, et al.
0

Dialog modelling faces a difficult trade-off. Models are trained on a large amount of text, yet their responses need to be limited to a desired scope and style of a dialog agent. Because the datasets used to achieve the former contain language that is not compatible with the latter, pre-trained dialog models are fine-tuned on smaller curated datasets. However, the fine-tuning process robs them of the ability to produce diverse responses, eventually reducing them to dull conversation partners. In this paper we investigate if prompting can mitigate the above trade-off. Specifically, we experiment with conditioning the prompt on the query, rather than training a single prompt for all queries. By following the intuition that freezing the pre-trained language model will conserve its expressivity, we find that compared to fine-tuning, prompting can achieve a higher BLEU score and substantially improve the diversity and novelty of the responses.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/22/2022

GODEL: Large-Scale Pre-Training for Goal-Directed Dialog

We introduce GODEL (Grounded Open Dialogue Language Model), a large pre-...
research
09/29/2020

The design and implementation of Language Learning Chatbot with XAI using Ontology and Transfer Learning

In this paper, we proposed a transfer learning-based English language le...
research
10/31/2019

Learning to Customize Language Model for Generation-based dialog systems

Personalized conversation systems have received increasing attention rec...
research
05/13/2020

Large Scale Multi-Actor Generative Dialog Modeling

Non-goal oriented dialog agents (i.e. chatbots) aim to produce varying a...
research
07/18/2023

Zero-shot Domain-sensitive Speech Recognition with Prompt-conditioning Fine-tuning

In this work, we propose a method to create domain-sensitive speech reco...
research
11/21/2021

Modelling Direct Messaging Networks with Multiple Recipients for Cyber Deception

Cyber deception is emerging as a promising approach to defending network...
research
05/08/2022

Context-Aware Abbreviation Expansion Using Large Language Models

Motivated by the need for accelerating text entry in augmentative and al...

Please sign up or login with your details

Forgot password? Click here to reset