Controllable Response Generation for Assistive Use-cases

12/04/2021
by   Shachi H Kumar, et al.
0

Conversational agents have become an integral part of the general population for simple task enabling situations. However, these systems are yet to have any social impact on the diverse and minority population, for example, helping people with neurological disorders, for example ALS, and people with speech, language and social communication disorders. Language model technology can play a huge role to help these users carry out daily communication and social interactions. To enable this population, we build a dialog system that can be controlled by users using cues or keywords. We build models that can suggest relevant cues in the dialog response context which is used to control response generation and can speed up communication. We also introduce a keyword loss to lexically constrain the model output. We show both qualitatively and quantitatively that our models can effectively induce the keyword into the model response without degrading the quality of response. In the context of usage of such systems for people with degenerative disorders, we present human evaluation of our cue or keyword predictor and the controllable dialog system and show that our models perform significantly better than models without control. Our study shows that keyword control on end to end response generation models is powerful and can enable and empower users with degenerative disorders to carry out their day to day communication.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/17/2022

Mars: Semantic-aware Contrastive Learning for End-to-End Task-Oriented Dialog

Traditional end-to-end task-oriented dialog systems first convert dialog...
research
12/12/2020

AffectON: Incorporating Affect Into Dialog Generation

Due to its expressivity, natural language is paramount for explicit and ...
research
09/08/2022

AARGH! End-to-end Retrieval-Generation for Task-Oriented Dialog

We introduce AARGH, an end-to-end task-oriented dialog system combining ...
research
10/31/2022

Controllable Factuality in Document-Grounded Dialog Systems Using a Noisy Channel Model

In this work, we present a model for document-grounded response generati...
research
07/28/2022

Interactive Evaluation of Dialog Track at DSTC9

The ultimate goal of dialog research is to develop systems that can be e...
research
12/15/2020

Keyword-Guided Neural Conversational Model

We study the problem of imposing conversational goals/keywords on open-d...
research
03/06/2018

An End-to-End Goal-Oriented Dialog System with a Generative Natural Language Response Generation

Recently advancements in deep learning allowed the development of end-to...

Please sign up or login with your details

Forgot password? Click here to reset