if we could have all the position paper presenters up at the front
and i think we have this microphone and the lapel mic there
so our first question is for format
who pointed out that there is already a commercial application
involving negotiation dialogs so what other kinds of application involving negotiation or non-cooperative dialogue can
you in addition
okay so
basically this is machines don't have any preferences
but they can express constraints so the negotiation between a user and a machine
general user that comes with preferences and machine that have
that has some constraints
and that the user is not aware
so than the most commonly deployed the negotiation dialogue system nowadays it's probably the appointment
scheduling
there has been a lot of work on the on this task
and
and it still i still walking quite pretty well
and but for the future even human operators are not too low to really negotiate
with the customers
so
i
i guess it's we want to load that for the four systems right now and
neither
but we can we can imagine that in the game industry there that would be
a lot of a lot of by gaining a stuff like this are trying to
trying to find a way to take information from characters
and stuff like this
the second question is for antenna how can we disentangle stance from sentiment emotion and
negotiation dialogue
i think there is like there's a lot of work and sentiment analysis and stands
recognition in every type of like text but defined a want to make is that
actually negotiation dialogue and especially argumentation
is that different scenario because actually liking this kind of context also like expression on
sentiment is used to express that stance
so it's more difficult to disambiguate need to
that's for sure and also like it could also be the case that you can
have like express no emotion can be used what than as an argument not claim
so i don't have a solution i just think it's more when we have to
deal will like negotiation and argumentation discourse in general this equation is much more complex
and so you have to model different dimension and not just like the pure semantics
of i sentence
the third question is for all good
how can well how can we collect
useful to date datasets for modeling negotiation dialogue
so actually i was examining how many negotiation dialogs we already corpora were already half
and we have pretty
pretty much or a well in different domains but my question was more a big
sv in this section session of you also have argumentative dialogues and what i recently
found out and which can be a quite useful and explore exceed the out the
visual content that we already have like
presidential debates
they are online you to put it up first i started to collect the design
scenarios for metal a corpus i branch true debates in interviews new yorker anti smoking
campaign and
good music is a most of them are already transcribed it's automatic speech recognition but
we can post correct can be save time on these
also a lot of gaming a lot of v t p d at the received
a bit db p at there is that i b m corpus features huge what
we
saved a lot of time on v gave to our professional school experts could meet
these negotiation dialogue and actually be a working a lot of these doctors who need
to convenes and negotiate is that patients shouldn't treatments
so or be designed for them some kind of content creating tools where they can
correct so information that the use and we can use these as a as a
is the two for collecting data
for simulating then extending down to retraining than
using this a real users
and also what they want to address is actually it's very sad everything kiss in
english
so there are
very few corpora for german there is a bit of dutch there is a bit
the french but not out the polish iso polish but well we all represents the
multilingual community it would be nice because
people need this actually in their own languages
for the of
thank you for that great point and the first question is for beth and what
would your like ideal shared task negotiation dialogue if we collected all this
things you suggested look like
well i think that the sort of corpora we've been talking about
be a little more challenging
and then have systems run on all sorts of corpora that would be the obvious
thing to do right
so
i mean even like the cut on corporate you could do that or some of
the corpora are the christian i we're suggesting if we had some of those collected
some of the existing corpora i think
would be best if they were actually negotiation oriented rather than just argumentative
because i think that we know less about what the language looks like in that
negotiation scenario
and particularly i think we know less about what it looks like in terms of
the prosody and the various ways that people actually express emotions and stance and things
like that are not
they're not well captured by just transcribing usually and so you really need to have
corpora that incorporate that and make you able to get it those things
we invite questions from the audience
i had a question about the collection based on jobs and emotional investment that
since people know that it's kind of just plucked is the more real jobs i
do still going to be emotionally invested
went out before we went out for real tool conference so that we wouldn't embarrass
anyone
that were pretty intense am i wrong way
where you would
i also from a particular experience i think if the simulation if the practise is
realistic enough
i think you're emotional apparatus kicks in pretty well and it will be identical to
the real thing but it is probably
pretty close
and you know would give you
it would give you this other scenario right which is more of a real-world scenario
i non gaming sort of real world scenarios
so this is kind of a comments and i guess not try to make it
into a question at some point but
so we
at usc we built this negotiation system on
looking at multi-issue bargaining with records and lance and creates a nice a little bit
about and one of the talks earlier
and one of the things we found is that you know well that kind of
system is easy to define are having apples and bananas since one we talk with
people to actually train others and how to negotiate
and what we found this the lot of the students people who are like doing
in b as learning how to really negotiate real world deals found these system so
simple as to seem almost irrelevant to the kinda negotiation they have to do and
and when you look at the sorts of things come up in real world negotiation
a lot of it is
it's very open ended in it's a very creative exercise a lot of times the
challenge one of the challenges is like figuring out what the even care about twenty
start out you don't know if it's apples or bananas maybe what they care about
is like hedging a certain kind of risk or something like that and you have
to do a lot of work to discover that
and then they can be quite creative and how they you know resolve those issues
so it may be able to insert some weird legal terms in the contract that
allow them to kinda
and meted out that risk that they perceive and so i think a challenge for
us as the
community trying to model the stuff computational use you know how do we get how
do we get into the space of all kind of the complexity of real world
kind of discussions that come up it and negotiation and i think in some cases
we can get there by looking at
things like job interviews where you it is a real-world scenario because you have pretty
standard things a get negotiated like salary in vacation and can i work remotely and
all those sorts of things
but i think are six sn kind of like having these things have impacts you
know depends on us kinda really engaging beyond
you know the bananas and apples and kind of getting in and two terms that
people that really need to learn these skills you know can benefit from
i guess my question is
do you need you guys
have ideas about kind of how do you how do you make this stuff appeal
you know and the real world to people that really need to learn to negotiate
at super important and really valuable to people
you know that i think that's important for the community
well it's very good question i i'm not claiming i can on so this hundred
percent but i think negotiation skills are quite complex and for some people a pot
of negotiation scale well what this negotiation skills what's involved is the presentation is that
approximation is that's up
money touring what the other is doing is it's reflecting go on what we try
to not to lock it was met the cognitive skills training so it's money during
what department is doing to find out trying to find out it's pretty his preferences
and act accordingly cooperatively non-cooperative lee and depending on your preferences to send to you
so
but did for politicians and that that's it and do formant not be dialogue system
in a sense of speech and vol still in perfect it was a bit though
for
annoying long but the apt negotiation aptitude built on they found the to very useful
and they like to use it to posts the game it was very engaging and
this so the poignant they try to train to calm to parental efficient outcome we
are no improvement is possible unless you hard out there
so and it was very useful for them are when they got what is the
sns
so i
i would say i wouldn't break down the negotiation skills in two
set of skills that are necessary and train maybe
we also have
i'm would be to
jumping from the also for people
to select themselves what be seeing for them is important to train
so i want to train joss presentation or i want to train a quality of
the arguments are present different my position or i want to train other
so maybe
to elaborate on that a little bit i think i one of the things that
attractive to me about negotiation is it's one of these domains where you can't do
it the way that you just rain through and do the
what rest italian restaurant is downtown you know it's complex and i think what we
need here is that classical we and in et al i which is to do
abstraction
right so i think that
the whole
the way you put together a system's gotta be at a different level of abstraction
then some of the systems that we've been seeing and i think that's the attraction
so we know that negotiation even if the simple a kind of what we've been
doing right now it's already very difficult because it's
it requires game theory elements is very difficult to train very difficult to have a
something that is not easily exploitable by their whether it with the player
so
it's a bit like a poker game somehow and
so you have to hide you information but at the same time you want to
you want to you want to get what you want
and so even it's
no very soon
simple form it's
it's already very difficult to solve
and if you add to this very complex so
right context make an is
it's very difficult to deal with it at all at once
well as that's why we built simulator that abstracted everything that is not the negotiation
game itself
i always thought that actually like a good weight to improve negotiation skills i like
the remediation so starting mediation unlike have a mediator of would i eight
actually it's i think it's a good way to understand what are like a controversial
fines and how to lexical what difference of opinion or how to being perceives e
and so on
alright well we are almost at the end of our time so i just want
to reiterate that
the position papers and links to the same down signal papers for the session are
on the sessions website as well as pointers to resources and a
bibliography
so thank you all for coming and i think the next session started three thirty