CueBot: Cue-Controlled Response Generation for Assistive Interaction Usages
Shachi H Kumar, Hsuan Su, Ramesh Manuvinakurike, Max Pinaroc, Sai Prasad, Saurav Sahay, Lama Nachman · 2022
Conversational assistants are ubiquitous among the general population, however, these systems have not had an impact on people with disabilities, or speech and language disorders, for whom basic day-to-day communication and social interaction is a huge struggle.Language model technology can play a huge role in empowering these users and help them interact with others with less effort via interaction support.To enable this population, we build a system that can represent them in a social conversation and generate responses that can be controlled by the users using cues/keywords.For an ongoing conversation, this system can suggest responses that a user can choose.We also build models that can speed up this communication by suggesting relevant cues in the dialog response context.We introduce a keyword-loss to lexically constrain the model response output.We present automatic and human evaluation of our cue/keyword predictor and the controllable dialog system to show that our models perform significantly better than models without control.Our evaluation and user 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.