ࡱ> ,.+  bjbjVV 4<< &&iiiii}}}} } jxxxsRixxxxxii444xjii4x4440}R40 4g4g44giHPxx4xxxxx4xxx xxxxgxxxxxxxxx& /: SPEAKER: Dr. Nava Tintarev Univerity of Aberdeen DATE: Wednesday the 21st of March 2012 TIME: 15:15 - 16:15 LOCATION: ֲý, Earl Mountbatten Building; room G.44 TITLE: Affecting people with Natural Language Generation ABSTRACT: This talk will describe three distinct case studies of affective NLG: explanations in recommender systems, augmented and assistive communication, and nature conservation. Recommender systems recommend items for a user to try or buy. Some, such as Amazon may try to support the recommendations with explanations such as "People like you also bought...". These explanations may be persuasive, or rather, help a user decide _not_ to try an item (that is not relevant for them). Did personalized explanations help people make better decisions? Story-telling, (including personal narrative), is a big part of our personal and social communication. We describe a way to "automatically" generate personal stories. The stories which are mix of natural language and multimedia, are based on sensor, and other data, collected with a mobile phone. This talk will place a particular focus on the natural language generation task of document structuring: segmenting this data into meaningful and distinct events. The MinkApp project assesses the use of NLG to assist nature conservation volunteers working on the Scottish Mink Initiative (SMI). This participatory initiative aims to safeguard species that are actively preyed upon by an invasive non-native species - the American mink. In such long-term and wide ranging initiatives, maintaining volunteer engagement can be challenging and volunteers must get feedback on their contributions to remain motivated to participate. Can spatio-temporal affective NLG help? SHORT BIO: Nava Tintarev is a Research Fellow in Natural Language Generation at the University of Aberdeen. Before that, she was at Telefonica Research, Barcelona, working on user-centered issues in recommender systems. Prior to that she completed her thesis on generating explanations for recommender systems (2009), a subject on which she received a best student paper award and co-authored a book chapter. She has also been an invited speaker at universities (ranging from UC3 Madrid to St Andrews) and local TechMeetups in Aberdeen and Edinburgh.    h PthNh Pth PtOJQJ 128YZ`noyB    gd Pt   gd Pt21h:pN. A!"#$% j 666666666vvvvvvvvv666666>6666666666666666666666666666666666666666666666666hH6666666666666666666666666666666666666666666666666666666666666666662 0@P`p2( 0@P`p 0@P`p 0@P`p 0@P`p 0@P`p 0@P`p8XV~ OJPJQJ_HmH nH sH tH J`J NNormal dCJ_HaJmH sH tH DA D Default Paragraph FontRiR 0 Table Normal4 l4a (k ( 0No List JZ`J  Pt0 Plain Text dCJOJQJaJF/F  Pt0Plain Text CharCJOJQJaJPK![Content_Types].xmlj0Eжr(΢Iw},-j4 wP-t#bΙ{UTU^hd}㨫)*1P' ^W0)T9<l#$yi};~@(Hu* Dנz/0ǰ $ X3aZ,D0j~3߶b~i>3\`?/[G\!-Rk.sԻ..a濭?PK!֧6 _rels/.relsj0 }Q%v/C/}(h"O = C?hv=Ʌ%[xp{۵_Pѣ<1H0ORBdJE4b$q_6LR7`0̞O,En7Lib/SeеPK!kytheme/theme/themeManager.xml M @}w7c(EbˮCAǠҟ7՛K Y, e.|,H,lxɴIsQ}#Ր ֵ+!,^$j=GW)E+& 8PK!Ptheme/theme/theme1.xmlYOo6w toc'vuر-MniP@I}úama[إ4:lЯGRX^6؊>$ !)O^rC$y@/yH*񄴽)޵߻UDb`}"qۋJחX^)I`nEp)liV[]1M<OP6r=zgbIguSebORD۫qu gZo~ٺlAplxpT0+[}`jzAV2Fi@qv֬5\|ʜ̭NleXdsjcs7f W+Ն7`g ȘJj|h(KD- dXiJ؇(x$( :;˹! I_TS 1?E??ZBΪmU/?~xY'y5g&΋/ɋ>GMGeD3Vq%'#q$8K)fw9:ĵ x}rxwr:\TZaG*y8IjbRc|XŻǿI u3KGnD1NIBs RuK>V.EL+M2#'fi ~V vl{u8zH *:(W☕ ~JTe\O*tHGHY}KNP*ݾ˦TѼ9/#A7qZ$*c?qUnwN%Oi4 =3ڗP 1Pm \\9Mؓ2aD];Yt\[x]}Wr|]g- eW )6-rCSj id DЇAΜIqbJ#x꺃 6k#ASh&ʌt(Q%p%m&]caSl=X\P1Mh9MVdDAaVB[݈fJíP|8 քAV^f Hn- "d>znNJ ة>b&2vKyϼD:,AGm\nziÙ.uχYC6OMf3or$5NHT[XF64T,ќM0E)`#5XY`פ;%1U٥m;R>QD DcpU'&LE/pm%]8firS4d 7y\`JnίI R3U~7+׸#m qBiDi*L69mY&iHE=(K&N!V.KeLDĕ{D vEꦚdeNƟe(MN9ߜR6&3(a/DUz<{ˊYȳV)9Z[4^n5!J?Q3eBoCM m<.vpIYfZY_p[=al-Y}Nc͙ŋ4vfavl'SA8|*u{-ߟ0%M07%<ҍPK! ѐ'theme/theme/_rels/themeManager.xml.relsM 0wooӺ&݈Э5 6?$Q ,.aic21h:qm@RN;d`o7gK(M&$R(.1r'JЊT8V"AȻHu}|$b{P8g/]QAsم(#L[PK-![Content_Types].xmlPK-!֧6 +_rels/.relsPK-!kytheme/theme/themeManager.xmlPK-!Ptheme/theme/theme1.xmlPK-! ѐ' theme/theme/_rels/themeManager.xml.relsPK]      8@0(  B S  ?$hr BN\^al 333333^}q QF~HxO^ Ptovk hN&\  @ @UnknownG* Times New Roman5Symbol3. * Arial7.{ @Calibri9=  K @ConsolasA BCambria Math"qh$G*GYY!20 2KX $P Pt2!xx Fiona Dick Fiona DickOh+'0t  0 < HT\dl Fiona Dick Normal.dotm Fiona Dick1Microsoft Office Word@@@Y՜.+,0 hp  ֲý   Title  !"$%&'()*-Root Entry F S/1Table gWordDocument4SummaryInformation(DocumentSummaryInformation8#CompObjy  F'Microsoft Office Word 97-2003 Document MSWordDocWord.Document.89q