Overview Discourse functions and devices, theory Augmenting Online - - PDF document

overview
SMART_READER_LITE
LIVE PREVIEW

Overview Discourse functions and devices, theory Augmenting Online - - PDF document

12/1/2008 Overview Discourse functions and devices, theory Augmenting Online Conversation applied through Automated Discourse Spark, a messaging architecture Tagging Tagging Video Vid Testing of Sparks advantages


slide-1
SLIDE 1

12/1/2008 1 Augmenting Online Conversation through Automated Discourse Tagging Tagging

Student Presentation: Brynjar

Overview

  • Discourse functions and devices, theory

applied

  • Spark, a messaging architecture

Vid

  • Video
  • Testing of Spark’s advantages
  • Questions?

Discourse functions and devices

  • Discourse functions dictate the

intent/content of communication

  • Discourse devices are the means to carry
  • ut this intent
  • ut this intent
  • Text chat lacks a lot of discourse devices
  • Reinvent missing devices, e.g. with Spark

Discourse functions

  • Interactional, make sure that the

conversation goes on accordingly with what the producers want

  • Transactional, “the pool of shared

, p knowledge”

  • Grounding
  • Mapping to a computable model:

Discourse model, entities and structure Rhematic: I come in peace

slide-2
SLIDE 2

12/1/2008 2

Discourse Devices

  • Getting and acknowledging attention with

visual cues

  • To transmit something rhematic, intonation

G di ith d

  • Grounding with a nod
  • Producing discourse structure transitions

with body language

Discourse devices, reloaded

  • Text only chat is a recipe for

misunderstanding, webcams suck

  • Avatars, virtual bodies to the rescue

U d t l

  • Use good gaze control
  • How about automated nodding and

appropriate handwaving as well?

Spark

  • Architecture to automatically diagnose and

transform simple chat text to markup with discourse information

  • Discourse markup transformed to
  • Discourse markup transformed to

behavioural markup

  • Behavioural markup interpreted to direct

an avatar

Markup example

slide-3
SLIDE 3

12/1/2008 3

Spark components

  • Discourse module

– POS with EngLite tagger – Finds lemma (root) of each word Head phrase (noun or verb) and head phrase – Head phrase (noun or verb) and head phrase modifier identification

  • Discourse context database
  • Avatar program

Video

Testing

  • Empirical
  • Objectively, time measured to finish task
  • Subjectively from questions answered by

ti i t participants

  • Success!

Questions?