Antonymy and Conceptual Vectors Didier Schwab, Mathieu Lafourcade, Violaine Prince Laboratoire d’informatique, de robotique Et de microélectronique de

Antonymy and

Conceptual Vectors

Didier Schwab, Mathieu Lafourcade, Violaine Prince

Laboratoire d’informatique, de robotiqueEt de microélectronique de MontpellierCNRS - Université Montpellier II

presented by Ch. Boitet (works with M. Lafourcade on conceptual vectors & UNL)

Schwab, Lafourcade, Prince, pres. by Ch. Boitet

Antonymy and Conceptual Vectors

Outline

The main idea Background on conceptual vectors How we use CVs

& why we need to distinguish CVs of antonyms

Brief study of antonymies Representation of antonymies Measure for « antonymousness »



The main idea Work on meaning representation in NLP,

using conceptual vectors (CV) applications = WSD & thematic indexing but V(existence) = V(non-existence) !

basic « concepts » activated the same

Idea: use lexical functions to improve the

adequacy For this, « transport » the lexical functions in

the vector space



Background on conceptual vectors

Lexical Item = ideas = combination of concepts = Vector V

Ideas space = vector space (generator space)

Concept = idea = vector Vc

Vc taken from a thesaurus hierarchy (Larousse) translation of Roget’s thesaurus, 873 leaf nodes the word ‘peace’ has non zero values for

concept PEACE and other concepts



Our conceptual vectors Thesaurus

• H : thesaurus hierarchy — K conceptsThesaurus Larousse = 873 concepts

• V(Ci) : <a1, …, ai, … , a873>aj = 1/ (2 ** Dum(H, i, j))

1/41 1/41/41/161/16 1/64 1/64

2 64



Conceptual vectors Concept c4: ‘PEACE’

peace

hierarchical relations

conflict relations

The world, manhood society



Conceptual vectors Term “peace”

c4:’PEACE’



finance

profitexchange



Angular or « thematic » distance

Da(x,y) = angle(x,y) = acos(sim(x,y))

= acos(x.y /|x ||y |) 0 ≤ D(x,y) ≤ (positive components) If 0 then x and y are colinear : same idea. If /2 : nothing in common.

x

y



Thematic Distance (examples)

Da(anteater , anteater ) = 0 (0°) Da(anteater , animal ) = 0,45 (26°) Da(anteater , train ) = 1,18 (68°) Da(anteater , mammal ) = 0,36 (21°) Da(anteater , quadruped ) = 0,42 (24°) Da(anteater , ant ) = 0,26 (15°)

thematic distance ≠ ontological distance



Vector Proximity

Function V gives the vectors closest to a lexical item.

V (life) = life, alive, birth…

V (death) = death, to die, to kill…



How we build & use conceptual vectors

Conceptual vectors give thematic representations of word senses of words (averaging CVs of word senses) of the content (« ideas ») of any textual segment

New CVs for word senses are permanently learned from NL definitions

coming from electronic dictionaries CVs of word senses are permanently

recomputed for French, 3 years, 100000 words, 300000 CVs



SYGMART Morphosyntactic analysis

DefinitionsHuman usage dictionaries

Conceptual vectorsbase

New Vector

Continuous building of the conceptual vectors

database



We should distinguish CVs of different but related

words…

Non-existent : who or which does not exist

cold : #ant# warm, hot Without a specific treatment, we get

V(non-existence) = V(existence)V(cold) = V(hot)

We want to obtainV(non-existence) ≠ V(existence) V(cold) ≠ V(hot)



Applications: more precision Thematic analysis of texts Thematic analysis of definitions

Resources: coherence & adequacy General coherence of the CV data

base Conceptual Vector quality (adequacy)

…in order to improve applications and resources



Lexical functions may help!

Lexical function (Mel’tchuk): WS {WS1…WSn}

synonymy (#Syn#), antonymy (#Anti#), intensification (#Magn#)…

Examples : #Syn# (car) = {automobile}#Anti# (respect) = {disrespect;

disdain}#Sing# (fleet) = {boat, ship;

embarcation}



Method: transport the LFs as functions on the CV

space

e.g. for antonymy,to get V(non-existence) ≠

V(existence)

find vector function Anti such that:V(non-existence)

= V(#Anti#(existence)) = Anti (V(existence))

similarly for other lexical functionswe simply began by studying antinomy



Brief study of antonymy

Definition : Two lexical items are in antonymy relation if

there is a symmetry between their semantic components relatively to an axis

Antonymy relations depend on the type of medium that supports symmetry

There are several types of antonymy On the axis, there are fixed points:

Anti (V(car)) = V(car) because #Anti# (car) =



1- Complementary antonymy

Values are boolean & symmetric (01)

Examples : event/non-event dead/alive

existence/non-existence

He is present He is not absentHe is absent He is not present



2- Scalar antonymy Values are scalar Symmetry is relative to a reference value

Examples : cold/hot, small/tall

This man is small This man is not tallThis man is tall This man is not small

This man is neither tall nor smallreference value = « of medium height »



3- Dual Antonymy (1)

Conversive dualssame semantics but inversion of roles

Examples : sell/buy, husband/wife, father/son

Jack is John’s son John is Jack’s father

Jack sells a car to John John buys a car from Jack



3- Dual Antonymy (2) Contrastive duals

contrastive expressions accepted by usage

Cultural : sun/moon, yin/yang

Associative : question/answer

Spatio-temporal : birth/death, start/finish



Learning bootstrap based on a kernel composed of pre-computed vectors considered as adequate

Learning must be coherent = preserve adequacy

Adequacy = judgement that activations of concepts (coordinates) make sense for the meaning corresponding to a definition

For coherence improvement, we use semantic relations between terms

Coherence and adequacy of the base



Based on the antonym vectors of concepts : one list for each kind of antonymy

Antic (EXISTENCE) = V (NON-EXISTENCE)

Antis (HOT) = V (COLD)Antic (GAME) = V (GAME)

Anti (X,C) builds the vector « opposite » of vector X in context C

Antonymy function



Construction of the antonym vector of X in

context C

The method is to focus on the salient notions in V(X) and V(C)

If the notions can be opposed, then the antonym should have the inverse ideas in the same proportions

The following formula was obtained after several experiments



AntiR (V(X), V(C)) = Pi *AntiC (Ci, V(C))

Pi = V * max (V(X), V(Ci))

Not symmetrical Stress more on vector X than on context C Consider an important idea of the vector to

oppose even if it is not in the referent

Construction of the antonym vector (2)

i=1N

Xi

1+CV(V(X))



Results

V (#Anti# (death, life & death)) = (LIFE 0,3), (birth 0,48), (alive 0,54)…

V (#Anti# (life, life & death)) = (death 0,336), (killer 0,45), (murdered

0,53)… V (#Anti# (LIFE))

= (DEATH 0,034), (death 0,43), (killer 0,53)...



Antonymy evaluation measure

Assess « how much » two lexical items are antonymous

Manti(A,B) = DA(AB, Anti(A,C) Anti(B,C))

A

B

Anti(B)

Anti(A)



Examples

Manti (EXISTENCE, NON-EXISTENCE) = 0,03

Manti (existence, non-existence) = 0,44 Manti (EXISTENCE, CAR) = 1,45 Manti (existence, car) = 1,06 Manti (CAR, CAR) = 0,006 Manti (car, car) = 0,407



Conclusion and perspectives

Progress so far : Antonymy definition based on a notion of symmetry Implemented formula to compute an antonym vector Implemented measure to assess the level of

antonymy between two items Perspectives :

Use of the symbolic opposition found in dictionaries Search the opposite meaning of a word Study of the other semantic relations

(hyperonymy/hyponymy, meronymy/holonymy…)

Documents

Antonymy and Conceptual Vectors Didier Schwab, Mathieu Lafourcade, Violaine Prince Laboratoire d’informatique, de robotique Et de microélectronique de