Abstract not found

Abstract. This paper proposes an account of the acquisition of grammatical relations using the basic concepts of connectionism and a construction-based theory of grammar. Many previous accounts of first-language acquisition assume that grammatical relations (e.g., the grammatical subject and object of a sentence) and linking rules are universal and innate; this is necessary to provide a first set of assumptions in the target language to allow deductive processes to test hypotheses and/or set parameters. In contrast to this approach, we propose that grammatical relations emerge rather late in the language-learning process. Our theoretical proposal is based on two observations. First, early production of childhood speech is formulaic and becomes systematic in a progressive fashion. Second, grammatical relations themselves are family-resemblance categories that cannot be described by a single parameter. This leads to the notion that grammatical relations are learned in a bottom up fashion. Combining this theoretical position with the notion that the main purpose of language is communication, we demonstrate the emergence of the notion of “subject ” in a simple recurrent network that learns to map from sentences to semantic roles. We analyze the hidden layer representations of the emergent subject, and demonstrate that these representations correspond to a radially–structured category. We also claim that the pattern of generalization and undergeneralization demonstrated by the network conforms to what we expect from the data on children’s generalizations. 1

rnating verbs in English (4) a. John stuffed feathers into the pillow Figure-frame b. John stuffed the pillow (with feathers) Ground-frame also, "paint", "wrap", or "stuff" Kim, Landau, and Phillips, BUCLD 23 11/7/98 2 . But.... The existence of cross-linguistic differences in the syntax of locative verbs undermines learning strategies based on universal mapping between syntax and semantics. Syntactic pattern of "fill"-class verb in Korean: Alternators (5) a. Yumi-ka mul-ul cep-e chaywu-ess-ta Nom water-Acc cup-Loc fill-past-Decl `*Yumi filled water into the container.' Figure-frame b. Yumi-ka cep-ul mul-lo chaywu-ess-ta Nom cup-Acc water-with fill-past-Decl `Yumi filled the container with water.' Ground-frame Syntactic pattern of "pile"-class verb in Korean: Figure verbs (6) a. Yumi-ka chaek-ul chaeksang-ey ssa-ass-ta Nom book-Acc table-Loc pile-past-Decl 'Yumi piled the books on the table.' Figure-frame b.

In learning a language, children must generalize over the utterances they hear so that they can creatively produce and understand utterances they have never heard before (Chomsky, 1957). Statistical properties of language have been demonstrated to enable formal generalizations

Abstract not found

Semantic roles are a critical aspect of linguistic knowledge because they indicate the relations of the participants in an event to the main predicate. Experimental studies on children and adults show that both groups use associations between general semantic roles such as Agent and Theme, and grammatical positions such as Subject and Object, even in the absence of familiar verbs. Other studies suggest that semantic roles evolve over time, and might best be viewed as a collection of verb-based or general semantic properties. A usage-based account of language acquisition suggests that general roles and their association with grammatical positions can be learned from the data children are exposed to, through a process of generalization and categorization. In this paper, we propose a probabilistic usage-based model of semantic role learning. Our model can acquire associations between the semantic properties of the arguments of an event, and the syntactic positions that the arguments appear in. These probabilistic associations enable the model to learn general conceptions of roles, based only on exposure to individual verb usages, and without requiring explicit labelling of the roles in the input. The acquired role properties are a good intuitive match to the expected properties of various roles, and are useful in guiding comprehension in the model to the most likely interpretation in the face of ambiguity. The learned roles can also be used to select the correct meaning of a novel verb in an ambiguous situation. 1

A note to the reader of these draft chapters These are my final draft chapters of Verbs: aspect and argument structure, to be published by Oxford University Press. Although they present a (somewhat revised) version of the model of aspect and argument structure in the draft chapters from 2000 that were formerly available on my website

The item-based nature of children’s early syntactic development