Increasing Faithfulness in Knowledge-Grounded Dialogue with Controllable Features

07/14/2021
by   Hannah Rashkin, et al.
0

Knowledge-grounded dialogue systems are intended to convey information that is based on evidence provided in a given source text. We discuss the challenges of training a generative neural dialogue model for such systems that is controlled to stay faithful to the evidence. Existing datasets contain a mix of conversational responses that are faithful to selected evidence as well as more subjective or chit-chat style responses. We propose different evaluation measures to disentangle these different styles of responses by quantifying the informativeness and objectivity. At training time, additional inputs based on these evaluation measures are given to the dialogue model. At generation time, these additional inputs act as stylistic controls that encourage the model to generate responses that are faithful to the provided evidence. We also investigate the usage of additional controls at decoding time using resampling techniques. In addition to automatic metrics, we perform a human evaluation study where raters judge the output of these controlled generation models to be generally more objective and faithful to the evidence compared to baseline dialogue systems.

READ FULL TEXT

page 4

page 13

research
09/19/2023

PICK: Polished Informed Candidate Scoring for Knowledge-Grounded Dialogue Systems

Grounding dialogue response generation on external knowledge is proposed...
research
12/22/2020

Learning to Retrieve Entity-Aware Knowledge and Generate Responses with Copy Mechanism for Task-Oriented Dialogue Systems

Task-oriented conversational modeling with unstructured knowledge access...
research
11/19/2019

Aging Memories Generate More Fluent Dialogue Responses with Memory Networks

The integration of a Knowledge Base (KB) into a neural dialogue agent is...
research
10/24/2020

"Nice Try, Kiddo": Ad Hominems in Dialogue Systems

Ad hominem attacks are those that attack some feature of a person's char...
research
03/30/2023

Elastic Weight Removal for Faithful and Abstractive Dialogue Generation

Ideally, dialogue systems should generate responses that are faithful to...
research
09/15/2023

Unleashing Potential of Evidence in Knowledge-Intensive Dialogue Generation

Incorporating external knowledge into dialogue generation (KIDG) is cruc...
research
05/17/2023

Boosting Distress Support Dialogue Responses with Motivational Interviewing Strategy

AI-driven chatbots have become an emerging solution to address psycholog...

Please sign up or login with your details

Forgot password? Click here to reset