Diapositive 1 |
Overwiew & Objectives |
lexical semantic representations | ||
conceptual vector model (cvm) | ||
autonomous learning by the system | ||
from a given Ç semantic space È (ontology) | ||
effects of swithing ontologies (general ó spec) | ||
global effects on the lexicon | ||
local effects on particular word | ||
ambiguity as noise | ||
towards self contained WSD annotations | ||
Ç I made a deposit at the bank È | ||
Þ Ç I made a deposit at the bank<g:money> È | ||
Conceptual vectors vector space |
An idea | ||
Concept combination Ñ a vector | ||
Idea space | ||
= vector space | ||
A concept | ||
= an idea = a vector V | ||
with augmentation: V + neighboorhood | ||
Meaning space | ||
= vector space + {v}* |
2D view of Ç meaning space È |
Conceptual vectors Thesaurus |
H : thesaurus hierarchy Ñ K concepts | ||
Thesaurus Larousse = 873 concepts | ||
V(Ci) : <a1, É, ai, É , a873> | ||
aj = 1/ (2 ** Dum(H, i, j)) | ||
Conceptual vectors Concept c4:peace |
Conceptual vectors Term ÒpeaceÓ |
Diapositive 8 |
Angular distance |
DA(x, y) = angle (x, y) | ||
0 £ DA(x, y) £ p | ||
if 0 then x & y colinear Ñ same idea | ||
if p/2 then nothing in common | ||
if p then DA(x, -x) with -x Ñ anti-idea of x |
Angular distance |
DA(x, y) = acos(sim(x,y)) | |||
DA(x, y) = acos(x.y/|x||y|)) | |||
DA(x, x) = 0 | |||
DA(x, y) = DA(y, x) | |||
DA(x, y) + DA(y, z) ³ DA(x, z) | |||
DA(0, 0) = 0 and DA(x, 0) = p/2 by definition | |||
DA(ax, by) = DA(x, y) with ab > 0 | |||
DA(ax, by) = p - DA(x, y) with ab < 0 | |||
DA(x+x, x+y) = DA(x, x+y) £ DA(x, y) |
Thematic distance |
Examples | ||
DA(tit, tit) = 0 | ||
DA(tit, passerine) = 0.4 | ||
DA(tit, bird) = 0.7 | ||
DA(tit, train) = 1.14 | ||
DA(tit, insect) = 0.62 |
Some vector operations |
2D view of weak contextualization |
Autonomous learning 1/2 |
Autonomous learning 2/2 |
Local expansion of vector space |
Diapositive 17 |
Diapositive 18 |
Lexical Distribution from Local density |
Diapositive 20 |
Diapositive 21 |
Last words |
Switching of representation | ||
coarse grained to fine grained Þ better semantic discrimation | ||
É and vice-versa Þ conservation of resource | ||
global and local test functions | ||
for vector quality assessment | ||
decision taking about level of representation | ||
detectors when combined to lexical functions (antonymy, etc.) | ||
the basis for | ||
self adjustement toward a vector space of constant density | ||
wsd as a reduction of noise (in context or out of context) | ||
unification of ontologies | ||
self emergent structuration of terminology | ||