Semantic%20Memory%20Knowledge%20Acquisition%20Through%20Active%20Dialogues

1
Semantic Memory Knowledge Acquisition Through
Active Dialogues

• Wlodzislaw Duch, Julian Szymanski

The knowledge representation using relations
between concepts and keywords is relatively
simple model for modeling language. However it
gives the possibilities for implementation quite
interesting linguistic competences, not
demonstrated by more sophisticated knowledge
models, for example frames used in CYC. One of
the presented linguistic abilities is a twenty
questions game based on semantic memory built on
relational model for knowledge representation.
The next linguistic competence of the implemented
system is to talk about possessed knowledge. The
presented interaction with the human user is
organized in form of active dialog. It shows how
artificial system uses predefined sentence
templates for acquiring new knowledge. We present
dialog scenarios for mining knowledge and discuss
the data acquired into semantic memory structures
using them.
2
Psycholinguistic models of the Semantic Memory

• Endel Tulving Episodic and Semantic Memory
  1972.
• Semantic memory refers to the memory of meanings
  and understandings.
• It stores concept-based, generic, context-free
  knowledge.
• Pernament container for general knowledge (facts,
  ideas, words etc).

Hierarchical Model Collins Quillian, 1969
Semantic network Collins Loftus, 1975
3
Semantic knowledge representation

• wCRK
• weight Concept Relation Keyword

Cobra
is_a animal is_a beast is_a being is_a brute is_a creature is_a entity is_a fauna is_a object is_a organism is_a reptile is_a serpent is_a snake is_a vertebrate has belly has body part has cell has chest has costa
CDV Concept Description Vector forms Semantic
Matrix
4
Idea for semantic data aquisition
Play 20 questions with Avatar! http//diodor.eti.p
g.gda.pl/p420q/newAjaxInterface.aspx Think
about animal system tries to guess it, asking
no more than 20 questions that should be
answered only with Yes or No. Given answers
narrows the subspace of the most probable
objects. System learns from the games obtains
new knowledge from interaction with the human
users.
Is it vertebrate? Y Is it mammal? Y Does it have
hoof? Y Is it equine? N Is it bovine? N Does it
have horn? N Does it have long neck? Y I guess
it is giraffe.
5
Algorithm for 20 questions game
, where p(keywordvi) is fraction of concepts for
which the keyword has value vi Subspace of
candidate concepts O(A) are selected according
to O(A) i dCDVi-ANSW is minimal
,where CDVi is a vector for i-concept and ANSW is
a partial vector of retrieved answers ? we can
deal with user mistakes choosing d gt minimal
6
Automatic data acquisition

• Basic semantic data obtained from aggregation of
  machine redable dictionaries Wordnet ConceptNet
  Sumo Ontology
• Used relations for semantic category animal
• Semantic space truncated using word popularity
  rank

• IC information content is an amount of
  appearances of the particular word in WordNet
  descriptions
• GR - GoogleRank is an amount of web pages
  returned by Google search engine for a given word
  
• BNC - are the words statistics taken from
  British National Norpus.
• ? Initial semantic space reduced to 94 objects
  and 72 features

7
Human interaction knowledge aquisition

• Data obtained from machine readable dictionaries
• Not complete
• Not Common Sence
• Sometimes specialised concepts
• Some errors
• Knowledge correction in the semantic space

, where W0 initial weight, initial knowledge
(from dictionaries) ANS answer given by user N
amount of answers ß - parametr for indicating
importance initial knowledge
8
Active Dialogues

• Dialogues with the user for obtaining new
  knowledge
• While system fails gues the object
• I give up. Tell me what did you think of?
• The concepts used in the game corrects the
  semantic space
• While two concepts has the same CDV
• Tell me what is characteristic for ltconcept1/2gt ?
• The new keywords for specified concepts are
  stored in the semantic memory
• While system needs more knowledge for same
  concept
• I dont have any particular knowledge about
  ltconceptgt. Tell me more about ltconceptgt.
• System obtains new keywords for a given concept.