0:00:14but i wanted to presented to a continuum of what nickel are presented them
0:00:22are you
0:00:24we created a an inquisition game
0:00:28that abstracted completely the natural language out from the game so basically we consider that
0:00:34the negotiation
0:00:38it's finding an agreement between two people
0:00:45that's not my
0:00:48it's fa an agreement between two people and
0:00:52and so both there are a number of options possible agreement between them
0:01:00both people have different preferences overall this set of possible agreements
0:01:06and they have to exchange in order to find the best possible way
0:01:10and what we found out
0:01:13so you know very simply for the you know very simplified way of
0:01:19of communicating the different options is that supposed to simple and when we put two
0:01:30trying to find an agreement together
0:01:35maybe they didn't the where some of them where more easygoing
0:01:41but in the n the best strategy for the system was quite the same
0:01:47so the continue the
0:01:51the well what we did what we're trying to do now is to of more
0:01:56complex options that are
0:01:58that's not the combination of several features so for instance issue of trying to set
0:02:04an appointment you have to specify the date you have to specify the power
0:02:10or if you want to exchange fruits like in the bargaining task
0:02:15well you have to define how many apple i mean the oranges you want and
0:02:21stuff like that so these are different features and you can have a much complex
0:02:27a set of actions
0:02:29that a i want the apples
0:02:32or a
0:02:35we can meet in the at any time on a on thursday
0:02:39stuff like this and it
0:02:40the number of action then explodes and it would be much more in an interesting
0:02:44to work on this
0:03:02but i actually need
0:03:04i other than that huh show and the unit can try to
0:03:12i mean they can start like to tease to show the example
0:03:30i know it was the presentation and the k
0:03:40so we start the
0:03:48i think that everybody here agrees that major challenge for the automatic analysis them negotiate
0:03:54negotiation dialogs
0:03:56is that a like modeling be disagreement space which is shaped it different participants in
0:04:02you process of arguing
0:04:04and actually at least it's of the art there like studied in argumentation mining that
0:04:08focuses on due to medic identification of like james and primacy is and all sounded
0:04:13types of relation linking them like that supports
0:04:17agreement or disagreement
0:04:19our have are the current methodologies do not find to what aspects easy to the
0:04:26treatment as scope over
0:04:29and we believe that this is actually important in order to predict registration strategies and
0:04:35also to understand like specific controversy in different contexts
0:04:42so therefore our research question is like how can we model these scope of disagreements
0:04:47you know comment that the context
0:04:49and on these grounds we proposed a to a level ontology an upper lever and
0:04:55the lower level ontology
0:04:57in order to model these agreement space so let's like take as example
0:05:04a discussion around like taken from change maybe you the a subgradient
0:05:09and so as you can see details all of the original post use like diversity
0:05:15is not about race
0:05:18and uncertainty common starts to be at i versus societies the society which have people
0:05:24from different backgrounds and cultures how does raise scamming to play
0:05:29and actually these two sentences are called out or this is how we call nh
0:05:36comments in our like upper level ontology by one random participant that is called like
0:05:43d in the skin
0:05:45that actually challenges like the assertion underlying the rhetorical question we do not a rhetorical
0:05:52question so you're joking right and you can do you know as we descended like
0:05:56talk to some black falls
0:05:59so it's clears the according to our ontology did these first to send its use
0:06:03in like orange in the original forest
0:06:06are a target
0:06:07and the comment is like a whole lot
0:06:10and so it is clear that the relation is that these agreements relation but actually
0:06:15you can i think an e like weekly understand what is challenge is not really
0:06:22like the each row of the statement it is the fact that it's the each
0:06:26roles of the person with like expressing statement
0:06:29so basically what is challenge is not be proposition but speech act so one pretty
0:06:35easy to use conditional like making an argument is that of like having your right
0:06:39to do so
0:06:41and so actually the user is claiming that like the speaker is biased
0:06:47then you original poster goes on and you like you provides an example take these
0:06:51example a white child we immigrated from change are yet this depressed persecution and the
0:06:56black and make an child even next door to each other
0:06:59the african american child was had another way someone childhood is accepted into college for
0:07:05this take a bigger city one channel from chain child that is rejected
0:07:10so in this case there is an adder user id that like calls out this
0:07:14time like the challenge is you know corrine somebody rejection event
0:07:19and it is like well it's hard to say which key it would have a
0:07:23better shot at getting into the same competitive school and then you can tune you
0:07:27like expressing like a these agreement again but towards like the last sentence of the
0:07:33original what was so that prosody should be about the result of experience in background
0:07:37not skin
0:07:39so in this case what is challenge is not the events but actually it's really
0:07:44like the you truth of deeper position
0:07:47another type of these agreement is they one expressed by be all actually like in
0:07:54commenting on d meaning of the verb novelty word by diversity
0:07:59which is also part of the last a statement which actually in like different linguistic
0:08:05theories is considered like an entity soft first order and d
0:08:10so there are also other types of relation you can also have like agreement relations
0:08:15for example like the original poster answers to user c and this is like no
0:08:20i agree
0:08:22that one what it was like trying to say or a to relations type that
0:08:26are hard to classify
0:08:29for example like when the what we jump was to a of words i delta
0:08:35so you e actually that they like
0:08:37you have or stating
0:08:42yes i just want to finish we award punch lines our pension is that these
0:08:48ontologies readable to leverage outer existing semantic and pragmatic layers of annotation
0:08:54and then reach the information the information that they provide and for example because relation
0:08:59between like these agreement relations and you types of targets that they select
0:09:05promises to improve the detection of like about those which are like a type of
0:09:12and so then we then we like these are like a more points of discussion
0:09:16that basically muir those that have already been addressed by dependencies
0:09:23thank you
0:09:46so i'm happy to announce it just happens like two weeks ago via released out
0:09:52the corpus and you corpus met the log multi-issue bargaining corpus in ldc catalog so
0:10:00i presented for all for our group in here in several on and that colleagues
0:10:05in grounding and cool build the cognitive model for the corpus for the corpus collection
0:10:10and for the future system and i will be present the system to model
0:10:15so what the corpus is about as a scenario is multi-issue bargaining so it's not
0:10:20just negotiation to buy banana or oranges is i issues based preferences involve therefore issuers
0:10:29it's integrated negotiation as win been situation
0:10:34it's featuring actually negotiation the value in my it's a complex negotiation strategic negotiation the
0:10:41domain it was real scenario took
0:10:46in a at the necessity of buttons past the anti smoking legislation also this each
0:10:53year of new york could force the debate on the on this one and it
0:10:58was not very efficient so they me to come immediate many by just need to
0:11:02come together and everything negotiate
0:11:04why is not walking a half adjustments so basically the corpus is collected to be
0:11:10is that a negotiation train there so dct council needs to train a to be
0:11:18trained to negotiate beginnings different body sit giddings business represent the thief
0:11:24against police officers against house insurance et cetera et cetera so the preferences brag even
0:11:31for them raise up references in the in a sense that the right couple of
0:11:39scenarios designs and because
0:11:43it was not real politicians involve by the out you again parliamentarians so that where
0:11:49got a preferences and they need to defend their positions no time constraints and they
0:11:55were instructed to a weight negotiate a negative agreement i will explain later tomorrow so
0:12:01the basically
0:12:03cannot be all they we're at college not to accept
0:12:09this preferred
0:12:11this preferred options
0:12:13so the we will release for parts of this corpus now we release human dialogues
0:12:20for to have a was eight subjects
0:12:24two thousand turns ten thousand tokens bill the release they next part more which is
0:12:31more argument that eve we had they need to defend their position we will release
0:12:36debate corpus on the same topic and we will release the evaluation corpus which is
0:12:41larger human
0:12:43machine dialogue or human machine dialogues
0:12:48corpus asr recordings and transcriptions and you can use these to retrain the speech recognition
0:12:54is obviously too small but you can use it for adaptations of the speaker diarisation
0:12:59is done manually correctly everything a high quality
0:13:06into format in many format's also dear and also transcriptions in t i is include
0:13:15down we have dialogue annotations or semantic and pragmatic annotations
0:13:21about nine cells and to vent that this out annotated this types six dives up
0:13:26before the dialogue acts discussed structuring acts rhetorical relations according to the newest eyes are
0:13:33stand that
0:13:36that's it and this is you your l where you can download the
0:13:40corpus if you have membership