(2) This property of discrete infinity characterizes EVERY human language; none consists of a finite set of sentences. The unchanged central goal of linguistic theory over the last fifty years has been and remains to give a precise, formal characterization of this property and then to explain how humans develop (or grow) and use discretely infinite linguistic systems. (Epstein and Hornstein 200...

We define sentence generalization and generalization diagrams via a special case of least general generalization (LGG) as applied to linguistic parse trees. Similarity measure between linguistic parse trees is developed as LGG operation on the lists of sub-trees of these trees. The diagrams introduced are representation of mapping between the syntactic generalization level and semantic generali...

Although much effort has been put into speech understanding systems there still exists a rather wide gap between acoustic recognition and linguistic interpretation. We propose a formalism for an extremely close interaction of acoustic recognition and higher level analysis. Instead of a strict horizontal interface at the level of hypothesized word sequences or lattices, a vertical interface to t...

This paper discusses a perceptron model of the learning and assignment of linguistic stress, using data from nineteen human languages. First, we point out some interesting parallels between aspects of the model and the constructs and predictions of metrical phonology, the linguistic theory of stress. Second, we develop a novel analysis of linguistic stress in terms of ease of perceptron-learnab...

In this paper, we investigate the multiple attribute decision making (MADM) problem based on the arithmetic and geometric aggregation operators with hesitant fuzzy linguistic information. Then, motivated by the idea of traditional arithmetic operation, we have developed some aggregation operators for aggregating hesitant fuzzy linguistic information: hesitant fuzzy linguistic weighted average (...

An investigation of cascaded and parallel deep neural networks for speech synthesis is conducted. In these systems, suprasegmental linguistic features (syllable-level and above) are processed separately from segmental features (phone-level and below). The suprasegmental component of the networks learns compact distributed representations of high-level linguistic units without any segmental infl...

We consider mapping unrestricted natural language to formal spatial representations. We describe ongoing work on a two-level machine learning approach. The first level is linguistic, and deals with the extraction of spatial information from natural language sentences, and is called spatial role labeling. The second level is ontological in nature, and deals with mapping this linguistic, spatial ...

Native tonal-language speakers exhibit reduced sensitivity to lexical tone differences within, compared to across, categories (higher-level linguistic category influence). Yet, sensitivity is enhanced among musically trained, non-tonal-language-speaking individuals (lower-level acoustics processing influence). The current study investigated the relative contribution of higher- and lower-level i...