CLDec 4, 2021

Controllable Response Generation for Assistive Use-cases

arXiv:2112.02246v1
Originality Incremental advance
AI Analysis

This work addresses the need for assistive technology to empower individuals with degenerative disorders like ALS in daily communication, representing an incremental improvement in controllable response generation.

The researchers tackled the problem of enabling conversational agents to assist people with neurological and communication disorders by developing a dialog system that allows users to control response generation using cues or keywords, showing that their models effectively incorporate keywords without degrading response quality and perform significantly better than uncontrolled models in human evaluations.

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.

Foundations

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

Your Notes