Explaining Language Universals in Connectionist Networks
نویسنده
چکیده
Across languages there are certain characteristics which they share. Linguists, trying to explain language universals, have come up with different theories: They argue for (1) the innatedness of general linguistic principles, (2) the communicative functions reflected in linguisitic structure, (3) the psychological demands placed upon language users, or (4) grammar-internal explanations. This paper tries to explain some of the morphological universals in the framework of a connectionist network, supporting the third approach. Employing simple recurrent networks, a series of experiments were done on various types of morphological rules. The results show that the model's performance mirrors the extent to which the different types of rules occur in natural languages. The paper explains how the model has discovered these universals.
منابع مشابه
Rethinking eliminative connectionism.
Humans routinely generalize universal relationships to unfamiliar instances. If we are told "if glork then frum," and "glork," we can infer "frum"; any name that serves as the subject of a sentence can appear as the object of a sentence. These universals are pervasive in language and reasoning. One account of how they are generalized holds that humans possess mechanisms that manipulate symbols ...
متن کاملRecursive Inconsistencies Are Hard to Learn: A Connectionist Perspective on Universal Word Order Correlations
Across the languages of the world there is a high degree of consistency with respect to the ordering of heads of phrases. Within the generative approach to language these correlational universals have been taken to support the idea of innate linguistic constraints on word order. In contrast, we suggest that the tendency towards word order consistency may emerge from non-linguistic constraints o...
متن کاملComputational modeling of dynamic decision making using connectionist networks
In this research connectionist modeling of decision making has been presented. Important areas for decision making in the brain are thalamus, prefrontal cortex and Amygdala. Connectionist modeling with 3 parts representative for these 3 areas is made based the result of Iowa Gambling Task. In many researches Iowa Gambling Task is used to study emotional decision making. In these kind of decisio...
متن کاملModeling Syntactic Devices: An Exploration of Language Evolution from Connectionist and Memetic Perspectives
This thesis introduces the subject of language evolution and provides insights into the evolution of several syntactic devices by modeling the acquisition of artificial languages by humans and neural networks. Previous work has shown that some linguistic universals can be learned by sequential-learning devices with no languagespecific biases (e.g., Ellefson & Christiansen, 2000; Christiansen & ...
متن کاملContext-free versus context-dependent constituency relations: A false dichotomy
In this paper I articulate a notion of constituency orthogonal both to classical and connectionist approaches. I shall consider three “structure-in-time” connectionist networks (Simple Recurrent Networks, Long Short-Term Memory Models, and Non-classical Connectionist Parsers). I shall argue that explaining compositionality by means of any of these models drives us to an information-processing b...
متن کامل