The sequential structure and variable length of speech data suggests the use of structural techniques such as Hidden Markov Models or Grammatical Inference systems. In contrast, geometric and classical (non-recurrent) connectionist methods deal with objects represented in a vector space. This means that some method has to be used to transform variable-length strings of parameters into d-dimensi...

This paper presents a new context-free parsing algorithm based on a bidirectional strictly horizontal strategy which incorporates strong top–down predictions (derivations and adjacencies). From a functional point of view, the parser is able to propagate syntactic constraints reducing parsing ambiguity. From a computational perspective, the algorithm includes different techniques aimed at the im...

The purpose of this study is to investigate the relationship between information flow and preferred argument structure across different text types. A number of studies in both ergative and accusative languages confirm Du Bois’ (1987) grammatical constrains. Chinese is neither an ergative nor accusative language. The results of my Chinese data do not truly confirm Du Bois’ constraints. Transitiv...

BACKGROUND: Classical aphasiology, based on the study of stroke sequelae, fuses speech fluency and grammatical ability. Nonfluent (Broca's) aphasia often is accompanied by agrammatism; whereas in the fluent aphasias grammatical deficits are not typical. The assumption that a similar relationship exists in primary progressive aphasia (PPA) has led to the dichotomization of this syndrome into flu...

In order to construct a generic grammatical resource for Arabic language, we have chosen to develop an Arabic grammar based on TAG formalism. Our choice is, especially, justified by complementarities that we have noticed between Arabic syntax and this grammatical formalism. This paper consists of two comparative studies. The first is between a set of unification grammars. The second is between ...

In this paper, an agent-based evolutionary computing technique is introduced, that is geared towards the automatic induction and optimization of grammars for natural language (grael). We outline three instantiations of the grael-environment: thegrael-1 system uses large annotated corpora to bootstrap grammatical structure in a society of autonomous agents, that tries to optimally redistribute g...

People behave as if they know the structure of their environment. Because people rarely study that structure explicitly, several theorists have postulated an implicit learning system that abstracts that structure automatically. An alternative view is that people respond to local structure that derives from global structure. Measures are developed that quantify structure in a set of stimuli, in ...

The present study-both qualitative and quantitative--explored fifty EFL learners’ preferences for receiving error feedback on different grammatical units as well as their beliefs about teacher feedback strategies. The study also examined the effect of the students’ level of writing ability on their views about the importance of teacher feedback on different error types. Data was gathered throug...

A RULE-BASED APPROACH FOR CONVERTING WIKIPEDIA CONTENT INTO SEMANTIC RELATIONS In this thesis, we propose a method for conversion from natural language into semantic relations. In this research, we focus on text written in highly unstructured form. The method is based on analysis of grammatical patterns of the sentences chosen from Wikipedia. Regular expressions are used for the generation of g...

Information extraction from textual data has various applications, such as semantic search. Learning from positive example have theoretical limitations, for many useful applications (including natural languages), substantial part of practical structure (CFG) can be captured by framework introduced in this paper. Our approach to automate identification of structural information is based on gramm...