Language Acquisition As Learning

C, honasky's proposition that language is handled hy a language-specific laeulty needs more justi|ieation. In language acquisition ill i)artieular, it is still in question whether the faculty is necessary or aot. We succeeded in explaining one eonstrainl oil language acquisition in terms of a general learning mechanism. This paper describes a mach ine learning s y s t e m Rhea applied to the domain of language acquisit ion and shows that Rhea call learn the tendency which children c o n f r o n t i n g lie',',' words Seelll to l lave. 1 I n t r o d u c t i o n Chomsky proposed that language is handled by a language specilic faculty, but this proposition has not been verified, especially ill the area o f lan guage acquisili(:)n. Although Berwick[1] showed tile existence of a special nlechanisnl sulfirielfl for the learning of syntax, there is still a question of whether or not the I l lecha. t l ls lB iS l l eCessa ry , l?lll "therlnore, his model does not explain acquisition of setnantics or eoncepis. These were simply presupposed. We started froln a geimral k!arning mecha niSlll alld succeeded ill explainiug a constraint on language acquisition. Children learldng their ill'st language face and solve a big prol)hun of induction. They lind (:)lit ]lOW w o r d s &l'e a s e d all(] ) ' e l a t ed Ic, o t h e r words from lilni(ed informal[on at a surprisingly ra.pid rate. Ill tim fieM of (leveli)pmental psychology, many kinds of constraints have been pro posed to accounl for this I>henonten(m. Most of these constraints (:olne froln the view that as sunles a specific fl'anlework far language acquisi tion, but there is altother view: language as an extension of other intellectuaJ faculties, and its acquisition as one resnlt of the universal learning p r o c e s s that leads to (mr acquisition of intellect. We want to explain the children's ability ill terms of tile latter view. '[ 'hus, we make a machine learning systenl, Rhea, which arcepts n-luple illplltS elms[sting of instances f ro ln it. donlains (one from each (IonlaJn) and creates the rules that delilnil the imssibh , torah[nations. This framework b, very ~;eeera[, and yet i[" we choose (mi(:,r wc.'lds and lingl, islic des('riplions for thetil as tWO input donlains, it can be seen as a language arquisilion system without language specific constraints. In this paper, we describe lhe nm<'hine h,arnin~ syslenl Rhea an(l its applicali<n: to Ihe donlain of language artluisition. We show [hal with(m! a pri(ll'i inl~.Jrulatio(I almut how outer worlds an, or,~anized, Rhea can learn lhe "'set ting for new word.~ '~, which children con['rc, ldillg f l e w w ( l r d s s(!elll t(I possess. The imim is how the model aeqlfir~,~ and tormalizes the "meaning" of an expression. To achiew, this aut(:mOrlmusly, Rhea has its own rep resenlati(m language for outer-worlds. If one lin guistir expression is repeatedly given along wilh (tifli, renl otHer-worlds, it builds up one ('OmnlOtl r(,im~senlati(m tbr ;tl] lhe (mt(,r-worlds. This in | e l ' l l a l I ' e [ H ' e s e l l l ; l l i o l l that has a Ol le I o ( ) t ie c o r r e s p o n d e n c e to a linguistic expressi(m is regar(led as the "meaning" of the expression iu our model. 2 C o n s t r a i n t s Ill order to ehicidate the rhildren's rapid a('quisit[on of wmahulal'y, constraints ou~ the possible hypotheses about I[1(. meanings of linguistir e× pressions hay:' heen postulaled. ('lark[2] pro poses lh~ prhzciplf of eo'rdrasl whereby every two forlns ec.lltrast ill Illeallill~, anIl Marklnan[:l] suggests a Sll'Oll,l~el' ass~Hnplio~t of tft3"011Otllie tll'(](l+ nizatiom The assunlp!ion of lax(re,male organizalioll cold[lieS children Io assumil:g lhal a wc.r(l ,givell with all unknown objert refers Io a taxonomic class of the ob.iert. As ostensive d<,finitioll is the only way to acquire early wwabulary, the assumption reduces the possihle search space of area.sing. With this assulnlHion, if yoa see son.eone point Io an un familiar objec! and say a word, VOII Call i)resll(lle that I It(, word is eil her ! he label of lhe object or the label of one of Ihe categories it belongs Io and can li~rget about the possibility of the word 's I'(!l'('l'l'illg I(I O11(' (If i t s a t t r i b t l t ( ' s o r AcrEs DE COLING-92, NANTES, 23-28 ^ofrr 1992 7 0 7 I'ROC. OF COLING-92, NA~rrEs, AUG. 23-28, 1992 ( Represent Classify _ _ Generalize )