AUTHOR=Greco Claudio , Bagade Diksha , Le Dieu-Thu , Bernardi Raffaella 

TITLE=She adapts to her student: An expert pragmatic speaker tailoring her referring expressions to the Layman listener

JOURNAL=Frontiers in Artificial Intelligence

VOLUME=Volume 6 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2023.1017204

DOI=10.3389/frai.2023.1017204

ISSN=2624-8212

ABSTRACT=Communication is a dynamic process through which interlocutors adapt
to each other. In the development of conversational agents, this core
aspect has been put aside for several years since the main challenge
was to obtain conversational neural models able to produce utterances
and dialogues that at least at surface level are human-like.
Now that this milestone has been achieved, the importance of paying attention to the
dynamic and adaptive interactive aspect of language has been advocated
in several position papers. 

In this paper, we focus on how a Speaker adapts to an interlocutor
with different background knowledge.
Our models undergo a
pre-training phase, through which they acquire grounded knowledge by
learning to describe an image, and an adaptive
phase through which a Speaker and a Listener play a repeated reference
game. \citet{hawkins2020:continual} study how conversational models
create new conventions; we are interested, instead, in studying whether the
Speaker learns from the Listener's mistakes to adapt to his  background knowledge.

We evaluate models based on Rational Speech Act (RSA), a likelihood
loss, and a combination of the two. We show that RSA indeed could work
as a backbone to drive the Speaker towards the Listener: in the
combined model, the
communication becomes more successful, in terms of 
Listener's accuracy, and the language generated by the Speaker features changes
that signal an adaptation to the Listener's background knowledge: the
captions describing unknown object categories contain more
adjectives and less direct reference to the unknown objects.