WP3: Language Evolution

1
WP3 Language Evolution

• Paul Vogt
• Federico Divina
• Tilburg University

2
Objectives (from Annex I)

• to design a population such that it is capable
  of evolving one (or possibly more) languages that
  enables them to optimize cooperation.
• A secondary objective is to design the experiment
  such that the agents will discover communication
  as a useful strategy and find ways to use this
  strategy effectively.

3
Tasks

• Task 3.1 Define () the required set-up for
  evolving language, learning how to use
  communication and how to react properly on
  linguistic communication (). Year 1 M3.1
• Task 3.2 Implement the code for under 3.1 defined
  specifications and integrating the results
  achieved in tasks 2.2 and 2.3. Year 2 D3.1
• Task 3.3 Perform experiments with the system as
  implemented in task 3.2. Started Year 2
• Task 3.4 Report on the experiments performed.
  Started Year 2

4
Overview

• State of WP3
• Language games
• Preliminary results
• Social learning of skills
• Outlook final year
• Conclusions

5
Language games
Form
Cabbage
Referent
6
Aspects of language learning

• Establishing joint attention
• pointing
• Cross-situational learning
• statistical co-occurrences across situations
• Feedback
• not reliable
• Principle of contrast
• associations with existing meanings lower initial
  score

7
Experiments

• Aim To test effect of learning mechanisms on
  language development
• Conditions
• Fixed controller (no individual learning)
• Reproduction, but no evolution
• Socialness gene randomly set
• Possible actions move, turn, pick-up, eat, mate,
  talk shout
• Possible topics features of one object
• Fixed categories
• Initial population size 100
• Simulated for 36,500 time steps (100 NTYears)

8
Some statistics

• Per time step 27 language games initiated
  (total simulation 1 million games)
• 42 of games accompanied by pointing gesture
• 12 of games accompanied by feedback signal
• 50 of games no pointing, nor feedback

9
Varying No. of Features
Divina Vogt, Proc. EELC, 2006
10
Excluding learning mechanisms
Vogt Divina, Interaction Studies, in press
11
Social learning

• Assuming communication has evolved, how can
  language be used to acquire new skills?

12
Example
A1
h
f
E
hungry,have-food, eat
h,f,E
13
Example
A1
A2
h
h
T
E
f
M
T
E
L
h,f,T
h,f,E
hungry,no-food,talk
14
Example
A2
h
T
E
M
E
L
h,f,T
h,f,E
15
Example
A2
h
T
E
f
M
T
E
L
h,f,T
h,f,E
16
Will it work?

• Good question, we dont know...
• RL has (at least) 2 ways of deciding which nodes
  to insert
• Random insertion
• Intelligent insertion
• Our feeling is that second option could be more
  effective and integrates language evolution
  social learning elegantly

17
Outlook final year

• Integrating social learning (mostly done) also
  using telepathy
• Performing experiments to
• Improve model regarding accuracy
• Evolve language that aids survival social
  learning
• Focus of interest
• Language diffusion
• Emergence of dialects
• Social learning
• (Grammar)
• Define language specific challenges

18
Conclusions

• Made great progress
• Language games work well beyond chance, but could
  be improved
• Social learning of skills defined, implemented,
  but not integrated
• Still much to do...