dialogue   2247

« earlier    

What Climbing Expeditions Tell Us about Teamwork | Stanford Graduate School of Business
“If you’re going to host a town hall to inspire employees of your company to work together in achieving the company’s mission, then you want to encourage team values. Have everybody wear the same T-shirt,” Greer says. “But if you’re trying to make a strategic decision within a team, then make sure to highlight the differences in the room. Call people out based on their expertise.”
INTERESTING  ruffian  leftfield  dialogue  cognitivediversity  disagreement 
12 days ago by Walpole
RT : Why it's hard to talk about dialogic containers in English.
facilitation  dialogue  from twitter
16 days ago by adrianh
[1906.00141] Multi-Turn Beam Search for Neural Dialogue Modeling
In neural dialogue modeling, a neural network is trained to predict the next utterance, and at inference time, an approximate decoding algorithm is used to generate next utterances given previous ones. While this autoregressive framework allows us to model the whole conversation during training, inference is highly suboptimal, as a wrong utterance can affect future utterances. While beam search yields better results than greedy search does, we argue that it is still greedy in the context of the entire conversation, in that it does not consider future utterances. We propose a novel approach for conversation-level inference by explicitly modeling the dialogue partner and running beam search across multiple conversation turns. Given a set of candidates for next utterance, we unroll the conversation for a number of turns and identify the candidate utterance in the initial hypothesis set that gives rise to the most likely sequence of future utterances. We empirically validate our approach by conducting human evaluation using the Persona-Chat dataset, and find that our multi-turn beam search generates significantly better dialogue responses. We propose three approximations to the partner model, and observe that more informed partner models give better performance.
beam-search  dialogue 
17 days ago by arsyed
Roy Peter Clark: 12 things I learned (or re-learned) about storytelling from watching ‘Game of Thrones’ – Poynter
In narratives, dialogue is not explanatory. It is a form of action, something experienced – overheard – by the audience. We think of “Game of Thrones” as a medieval fantasy adventure, in many ways an homage to Tolkien. But for a series known for its action, much of what we get, and appreciate, is talk, talk, talk.
narrative  got  dialogue  t 
18 days ago by paulbradshaw
Fact-Checking the ‘Goodfellas’ “Funny Like a Clown” Speech - The Ringer
(This is maybe the canonical breakdown of Goodfellas’ “Funny Like a Clown” scene, complete with the dialogue in its entirety—)
“During the hangout, Tommy tells a story that prompts Henry to tell Tommy he’s a funny guy, which Tommy pretends to take as an insult. It’s a scene that has since aged into lore. It’s frenetic. It’s intimidating. It’s got just the right blend of boiling tension and uneasy confrontation and humor. But is it … true?

“Let’s fact-check it.”
goodfellas  funny  dialogue  theringer  2016 
19 days ago by handcoding
RT : R.I.P. Albert Rohan. We last spoke intensely about the in the summer of 2017. Inspiri…
Pristina  Dialogue  Belgrade  from twitter
19 days ago by nwhyte
[1902.08654] What makes a good conversation? How controllable attributes affect human judgments
A good conversation requires balance -- between simplicity and detail; staying on topic and changing it; asking questions and answering them. Although dialogue agents are commonly evaluated via human judgments of overall quality, the relationship between quality and these individual factors is less well-studied. In this work, we examine two controllable neural text generation methods, conditional training and weighted decoding, in order to control four important attributes for chitchat dialogue: repetition, specificity, response-relatedness and question-asking. We conduct a large-scale human evaluation to measure the effect of these control parameters on multi-turn interactive conversations on the PersonaChat task. We provide a detailed analysis of their relationship to high-level aspects of conversation, and show that by controlling combinations of these variables our models obtain clear improvements in human quality judgments.
conversation  dialogue 
20 days ago by arsyed
Overcoming Us vs. Them
Susan Fiske finds that we tend to categorize Thems along two axes: “warmth” and “competence”... as you imagine her sitting at dinner, enjoying that food, you are thinking of her as an individual, the surest way to weaken automatic categorization of someone as a Them....Replace essentialism with individuation:
dialogue  prejudice  ingroup  tribalism  fiske  sapolsky 
25 days ago by Walpole

« earlier    

related tags

2011  2016  2019  accents  adhd  aeon  agents  ai  andyclark  anger  animation  argument  array  attention  audio  author  beam-search  being  belgrade  beliefs  bots  brain  business  callard  children  civility  clarity  classideas  climatechange  clintonstudy  closedcaptioning  closedcaptions  cmv  cobeing  cognitivediversity  compression  conflict  consciousness  constructivist  conversation  conversations  cooperation  corpus  crisisneg  crowds  culturalpsych  curiosity  cybernetics  data  dataset  datasets  decisionmaking  deepadaptation  delusions  democracy  design  dialogic  dimentionality  diplomacy  disagreement  distractions  drawn  editing  editor  education  elearning  embodiment  emotion  environment  erisology  event  expectations  facilitation  feelreal  filler  film  fiske  french  funny  games  gdc19  generationz  genre  genz  gimbel  goodfellas  got  gradualism  groups  hbr  hearing  heteroglossia  hostageneg  howwelearn  howweread  humanism  ingroup  innovation  intelligence  interaction  interesting  internet  interpersonal  johnson  kazakhstan  lanceulnoff  language  languagelearning  languages  learning  leftfield  liberals  linguistics  listening  literacy  matrix  media  medium  memorization  memory  mikhailbakhtin  minsky  multimedia  multiple  narrative  neuralnets  neuroscience  nlp  norms  ocd  online  onlineescalation  organization  parenting  pcg  peace  pedagogy  perception  perspective  philosophy  polarisation  politics  polyphony  power  prejudice  pristina  processing  quotes  r  reading  reagan  reason  reference  rhetoric  rightingreflex  rray  ruffian  sapolsky  sebastiangreger  selftalk  short-film  socialmedia  socrates  sound  sovietunion  speech  status  structural  structure  students  studies  subtitles  t  talhelm  talk  tay  teaching  tech  technology  television  text  theringer  tiedens  timharford  tips  tomstafford  tribalism  tv  ui  uniqueness  ux  verbs  video  voice  weekly-guide  wikipedia  writing 

Copy this bookmark: