0:00:16if we could have all the position paper presenters up at the front
0:00:21and i think we have this microphone and the lapel mic there
0:00:26so our first question is for format
0:00:31who pointed out that there is already a commercial application
0:00:34involving negotiation dialogs so what other kinds of application involving negotiation or non-cooperative dialogue can
0:00:40you in addition
0:00:44okay so
0:00:46basically this is machines don't have any preferences
0:00:50but they can express constraints so the negotiation between a user and a machine
0:00:56general user that comes with preferences and machine that have
0:01:02that has some constraints
0:01:04and that the user is not aware
0:01:09so than the most commonly deployed the negotiation dialogue system nowadays it's probably the appointment
0:01:16scheduling
0:01:18there has been a lot of work on the on this task
0:01:21and
0:01:24and it still i still walking quite pretty well
0:01:31and but for the future even human operators are not too low to really negotiate
0:01:39with the customers
0:01:41so
0:01:42i
0:01:44i guess it's we want to load that for the four systems right now and
0:01:49neither
0:01:50but we can we can imagine that in the game industry there that would be
0:01:55a lot of a lot of by gaining a stuff like this are trying to
0:02:00trying to find a way to take information from characters
0:02:08and stuff like this
0:02:14the second question is for antenna how can we disentangle stance from sentiment emotion and
0:02:20negotiation dialogue
0:02:27i think there is like there's a lot of work and sentiment analysis and stands
0:02:31recognition in every type of like text but defined a want to make is that
0:02:36actually negotiation dialogue and especially argumentation
0:02:40is that different scenario because actually liking this kind of context also like expression on
0:02:47sentiment is used to express that stance
0:02:50so it's more difficult to disambiguate need to
0:02:54that's for sure and also like it could also be the case that you can
0:03:00have like express no emotion can be used what than as an argument not claim
0:03:07so i don't have a solution i just think it's more when we have to
0:03:11deal will like negotiation and argumentation discourse in general this equation is much more complex
0:03:17and so you have to model different dimension and not just like the pure semantics
0:03:23of i sentence
0:03:30the third question is for all good
0:03:32how can well how can we collect
0:03:36useful to date datasets for modeling negotiation dialogue
0:03:42so actually i was examining how many negotiation dialogs we already corpora were already half
0:03:47and we have pretty
0:03:49pretty much or a well in different domains but my question was more a big
0:03:55sv in this section session of you also have argumentative dialogues and what i recently
0:04:01found out and which can be a quite useful and explore exceed the out the
0:04:07visual content that we already have like
0:04:10presidential debates
0:04:12they are online you to put it up first i started to collect the design
0:04:18scenarios for metal a corpus i branch true debates in interviews new yorker anti smoking
0:04:27campaign and
0:04:29good music is a most of them are already transcribed it's automatic speech recognition but
0:04:36we can post correct can be save time on these
0:04:39also a lot of gaming a lot of v t p d at the received
0:04:43a bit db p at there is that i b m corpus features huge what
0:04:49we
0:04:50saved a lot of time on v gave to our professional school experts could meet
0:04:56these negotiation dialogue and actually be a working a lot of these doctors who need
0:05:01to convenes and negotiate is that patients shouldn't treatments
0:05:05so or be designed for them some kind of content creating tools where they can
0:05:12correct so information that the use and we can use these as a as a
0:05:20is the two for collecting data
0:05:23for simulating then extending down to retraining than
0:05:29using this a real users
0:05:31and also what they want to address is actually it's very sad everything kiss in
0:05:36english
0:05:38so there are
0:05:40very few corpora for german there is a bit of dutch there is a bit
0:05:44the french but not out the polish iso polish but well we all represents the
0:05:50multilingual community it would be nice because
0:05:53people need this actually in their own languages
0:05:57for the of
0:06:01thank you for that great point and the first question is for beth and what
0:06:05would your like ideal shared task negotiation dialogue if we collected all this
0:06:10things you suggested look like
0:06:15well i think that the sort of corpora we've been talking about
0:06:20be a little more challenging
0:06:22and then have systems run on all sorts of corpora that would be the obvious
0:06:26thing to do right
0:06:28so
0:06:30i mean even like the cut on corporate you could do that or some of
0:06:33the corpora are the christian i we're suggesting if we had some of those collected
0:06:38some of the existing corpora i think
0:06:42would be best if they were actually negotiation oriented rather than just argumentative
0:06:47because i think that we know less about what the language looks like in that
0:06:53negotiation scenario
0:06:56and particularly i think we know less about what it looks like in terms of
0:07:00the prosody and the various ways that people actually express emotions and stance and things
0:07:10like that are not
0:07:12they're not well captured by just transcribing usually and so you really need to have
0:07:17corpora that incorporate that and make you able to get it those things
0:07:25we invite questions from the audience
0:07:41i had a question about the collection based on jobs and emotional investment that
0:07:46since people know that it's kind of just plucked is the more real jobs i
0:07:52do still going to be emotionally invested
0:08:02went out before we went out for real tool conference so that we wouldn't embarrass
0:08:06anyone
0:08:08that were pretty intense am i wrong way
0:08:12where you would
0:08:16i also from a particular experience i think if the simulation if the practise is
0:08:24realistic enough
0:08:26i think you're emotional apparatus kicks in pretty well and it will be identical to
0:08:32the real thing but it is probably
0:08:35pretty close
0:08:37and you know would give you
0:08:40it would give you this other scenario right which is more of a real-world scenario
0:08:45i non gaming sort of real world scenarios
0:09:00so this is kind of a comments and i guess not try to make it
0:09:04into a question at some point but
0:09:06so we
0:09:08at usc we built this negotiation system on
0:09:14looking at multi-issue bargaining with records and lance and creates a nice a little bit
0:09:19about and one of the talks earlier
0:09:21and one of the things we found is that you know well that kind of
0:09:25system is easy to define are having apples and bananas since one we talk with
0:09:29people to actually train others and how to negotiate
0:09:33and what we found this the lot of the students people who are like doing
0:09:39in b as learning how to really negotiate real world deals found these system so
0:09:47simple as to seem almost irrelevant to the kinda negotiation they have to do and
0:09:54and when you look at the sorts of things come up in real world negotiation
0:09:59a lot of it is
0:10:01it's very open ended in it's a very creative exercise a lot of times the
0:10:07challenge one of the challenges is like figuring out what the even care about twenty
0:10:11start out you don't know if it's apples or bananas maybe what they care about
0:10:15is like hedging a certain kind of risk or something like that and you have
0:10:19to do a lot of work to discover that
0:10:22and then they can be quite creative and how they you know resolve those issues
0:10:28so it may be able to insert some weird legal terms in the contract that
0:10:34allow them to kinda
0:10:35and meted out that risk that they perceive and so i think a challenge for
0:10:40us as the
0:10:42community trying to model the stuff computational use you know how do we get how
0:10:46do we get into the space of all kind of the complexity of real world
0:10:51kind of discussions that come up it and negotiation and i think in some cases
0:10:56we can get there by looking at
0:10:59things like job interviews where you it is a real-world scenario because you have pretty
0:11:05standard things a get negotiated like salary in vacation and can i work remotely and
0:11:10all those sorts of things
0:11:13but i think are six sn kind of like having these things have impacts you
0:11:18know depends on us kinda really engaging beyond
0:11:22you know the bananas and apples and kind of getting in and two terms that
0:11:26people that really need to learn these skills you know can benefit from
0:11:32i guess my question is
0:11:34do you need you guys
0:11:37have ideas about kind of how do you how do you make this stuff appeal
0:11:42you know and the real world to people that really need to learn to negotiate
0:11:46at super important and really valuable to people
0:11:49you know that i think that's important for the community
0:11:54well it's very good question i i'm not claiming i can on so this hundred
0:11:59percent but i think negotiation skills are quite complex and for some people a pot
0:12:04of negotiation scale well what this negotiation skills what's involved is the presentation is that
0:12:10approximation is that's up
0:12:13money touring what the other is doing is it's reflecting go on what we try
0:12:17to not to lock it was met the cognitive skills training so it's money during
0:12:21what department is doing to find out trying to find out it's pretty his preferences
0:12:28and act accordingly cooperatively non-cooperative lee and depending on your preferences to send to you
0:12:34so
0:12:36but did for politicians and that that's it and do formant not be dialogue system
0:12:42in a sense of speech and vol still in perfect it was a bit though
0:12:46for
0:12:48annoying long but the apt negotiation aptitude built on they found the to very useful
0:12:55and they like to use it to posts the game it was very engaging and
0:13:01this so the poignant they try to train to calm to parental efficient outcome we
0:13:08are no improvement is possible unless you hard out there
0:13:12so and it was very useful for them are when they got what is the
0:13:17sns
0:13:19so i
0:13:21i would say i wouldn't break down the negotiation skills in two
0:13:26set of skills that are necessary and train maybe
0:13:31we also have
0:13:32i'm would be to
0:13:34jumping from the also for people
0:13:37to select themselves what be seeing for them is important to train
0:13:42so i want to train joss presentation or i want to train a quality of
0:13:48the arguments are present different my position or i want to train other
0:13:54so maybe
0:13:59to elaborate on that a little bit i think i one of the things that
0:14:02attractive to me about negotiation is it's one of these domains where you can't do
0:14:08it the way that you just rain through and do the
0:14:12what rest italian restaurant is downtown you know it's complex and i think what we
0:14:19need here is that classical we and in et al i which is to do
0:14:23abstraction
0:14:25right so i think that
0:14:26the whole
0:14:27the way you put together a system's gotta be at a different level of abstraction
0:14:32then some of the systems that we've been seeing and i think that's the attraction
0:14:46so we know that negotiation even if the simple a kind of what we've been
0:14:51doing right now it's already very difficult because it's
0:14:55it requires game theory elements is very difficult to train very difficult to have a
0:15:01something that is not easily exploitable by their whether it with the player
0:15:09so
0:15:11it's a bit like a poker game somehow and
0:15:15so you have to hide you information but at the same time you want to
0:15:18you want to you want to get what you want
0:15:22and so even it's
0:15:25no very soon
0:15:26simple form it's
0:15:28it's already very difficult to solve
0:15:30and if you add to this very complex so
0:15:34right context make an is
0:15:36it's very difficult to deal with it at all at once
0:15:41well as that's why we built simulator that abstracted everything that is not the negotiation
0:15:47game itself
0:15:53i always thought that actually like a good weight to improve negotiation skills i like
0:16:00the remediation so starting mediation unlike have a mediator of would i eight
0:16:08actually it's i think it's a good way to understand what are like a controversial
0:16:14fines and how to lexical what difference of opinion or how to being perceives e
0:16:19and so on
0:16:30alright well we are almost at the end of our time so i just want
0:16:34to reiterate that
0:16:35the position papers and links to the same down signal papers for the session are
0:16:40on the sessions website as well as pointers to resources and a
0:16:44bibliography
0:16:45so thank you all for coming and i think the next session started three thirty