What precisely is the universal nature of the human syntactic parser, such that it copes easily with some embedded structures, yet fails so dramatically on others (e.g., classic double center-embeddings)? A theory is proposed in the form of an architecture for parsing based on two simple ideas. The first is that human short-term memory is an indexing structure which can give rise to interference effects (storage limitations) when contents overlap with respect to the indices. For parsing, the contents are syntactic structures, and the indices are potential structural relations. The second idea is that the capacity of STM is the minimum capacity required to support the basic functions of parsing. The theory successfully accounts for the contrasts between over 50 difficult and acceptable constructions from English, French, German, Hebrew, Japanese, Mandarin, and Spanish. The theory has independent psychological and computational motivation, and is a functional part of a broader cognitive ...

this paper the Lambek notation, in which the argument category is found under the slash, is applied. Consider for example the categorial representation of an intransitive verb: nps looks for an np to its left and results in an s

A natural language parser implemented entirely in simulated neurons is described. It produces a semantic representation based on frames. It parses solely using simulated fatiguing Leaky Integrate and Fire neurons, that are a relatively accurate biological model that is simulated efficiently. The model works on discrete cycles that simulate 10 ms. of biological time, so the parser has a simple mapping to psychological parsing time. Comparisons to human parsing studies show that the parser closely approximates this data. The parser makes use of Cell Assemblies and the semantics of lexical items is represented by overlapping hierarchical Cell Assemblies so that semantically related items share neurons. This semantic encoding is used to resolve prepositional phrase attachment ambiguities encountered during parsing. Consequently, the parser provides a neurally-based cognitive model of parsing.

A discussion of modularity in language production processes, with special emphasis on processes for retrieving words and building syntactic structures for a to-be-uttered sentence, is presented. The authors’ 1st goal was to assess the extent to which information processing is encapsulated between different processing stages. In particular, they assessed whether the input from one processing stage to the next is minimal and whether the flow of information in the system is strictly unidirectional. On the basis of the reviewed evidence, they conclude that both assumptions have to be revised. Their 2nd goal was to propose an alternative framework that does not assume strict encapsulation but that maintains multiple levels of integration for production. During the past 20 years a “great divide ” (as Boland & Cutler, 1996, p. 309, labeled it) has characterized the psycholinguistic world: Can the processes engaged during comprehension and production of language be conceived of as modular or not? Whereas a number of influential theories that do not assume a modular system have been put forward in the comprehension domain (e.g., MacDonald, Pearlmutter, & Seidenberg, 1994; Tabor

The parsing component of previous principle-based parsers are inefficient since they tend to adopt a generate-and-test paradigm. We combine the benefits of a message-passing paradigm with the benefits of a parametric approach in the implementation of a parser that avoids overgeneration and is easily ported to multiple languages. The algorithm has been implemented in C++ and successfully tested on well-known, translationally divergent sentences. We are currently incorporating the parser into a machine translation (MT) system called PRINCITRAN.

Abstract. The concept of Dynamic Neural Networks (DNN) is a new approach within the Neural Network paradigm, which is based on the dynamic construction of Neural Networks during the processing of an input. The DNN methodology has been employed in the Hybrid Connectionist Parsing (HCP) approach, which comprises an incremental, on-line generation of a Neural Network parse tree. The HCP ensures an adequate representation and processing of recursively defined structures, like grammar-based languages. In this paper, we describe the general principles of the HCP method and some of its specific Neural Network features. We outline and discuss the use of the HCP method with respect to parallel processing of ambiguous structures, and robust parsing of extra-grammatical inputs in the context of spoken language parsing. 1

Dynamical systems theory provides effective formal models of structure in natural languages. We describe a recurrent neural network called the Bramble Network (BRN) and a related analytical tool, the Dynamical Automaton (DA), which process words in sequence. The BRN makes one discrete jump across its state space each time a word is processed, and then settles continuously to a stable state. Processing time is modeled as convergence time. Two well-known phenomena in natural language processing are modeled: (i) the inverse correlation between word frequency and response time and (ii) the correlation between parsing difficulty and level of center embedding. The model shows how constructs of dynamical systems theory provide a link between neural network models which are good at learning and show human-like flexibility and abstract linguistic representations which are the current best model of natural language syntactic structure and interpretation. What role does dyna

This document can be downloaded via links at

Simulated Annealing, a wide-spread technique for combinatorial optimisation, is employed to find the optimal candidate in a candidate set, as defined in Optimality Theory (OT). Being a heuristic techniques, simulated annealing does not guarantee to return the correct solution, and yet, some result is always returned within a constant time. Similarly to language production, this time framework can be diminished with the cost of diminishing correctness. We demonstrate how simulated annealing can model linguistic performance, built upon a competence theory, namely, OT. After having applied simulated annealing to OT, we attempt to reproduce empirical observations on metrical stress in Dutch fast speech. Simulated annealing necessitates defining a topology on the candidate set, as well as an exact formulation of the constraint OUTPUT-OUTPUT CORRESPONDENCE.

A central question for psycholinguistics concerns the role of grammatical constraints in online sentence processing. Many current theories maintain that, at each point in time, the processor constructs an analysis which is consistent with the grammatical information in the input. Several bottom-up, dynamical models make a contrasting prediction: partial parses which are syntactically incompatible with the current input can nevertheless temporarily influence the processor. Three self-paced reading experiments demonstrated the influence of such local structural ambiguities. The first examined