Parsing Natural Language into Content for Storage and Retrieval in a Content-Addressable Memory
نویسنده
چکیده
Abstract. This paper explores the possibility of applying Database Semantic (DBS) to textual databases and the WWW. The DBS model of natural language communication is designed as an artificial cognitive agent with a hearer mode, a think mode, and a speaker mode. For the application at hand, the hearer mode is used for (i) parsing language data into sets of proplets, defined as non-recursive feature structures, which are stored in a content-addressable memory called Word Bank, and (ii) for parsing the user query into a DBS schema employed for retrieval. The think mode is used to expand the primary data activated by the query schema to a wider range of relevant secondary and tertiary data. The speaker mode is used to realize the data retrieved in the natural language of the query.
منابع مشابه
Using Relational Syntactic Constraints in Content - Addressable Memory Architectures for Sentence Parsing
How linguistic representations in memory are searched and retrieved during sentence processing is an active question in psycholinguistics. Much work has independently suggested that retrieval operations require constant-time computations, are susceptible to interference, and operate under the constraint of a severely limited focus of attention. These features suggest a model for sentence proces...
متن کاملDNA Hypernetworks for Information Storage and Retrieval
Content-addressability is a fundamental feature of human memory underlying many associative information retrieval tasks. In contrast to location-based memory devices, content-addressable memories require complex interactions between memory elements, which makes conventional computation paradigms difficult. Here we present a molecular computational model of content-addressable information storag...
متن کاملContent-Addressable and Associative Memory Systems a Survey
This review of content-addressable memory and as-A. Purpose of This Study sociative computer systems represents an attempt to consolidate and report nontechnically the direction in which numerous independent The primary purpose of this study is to provide in-research programs have progressed during the last ten years. The formation bases on which recommendations can be made paper reflects the v...
متن کاملNeural-net inference and content addressable memory
We consider Whittle's probabilistic content addressable memory, the antiphon, which is designed for recovering stored patterns from nonlinear distortions of the input messages. We give an application to content-based image retrieval systems and propose canonical ways of choosing similarity thresholds ensuring statistical consistency.
متن کاملHolographic digital data storage using phase- modulated pixels
We propose and demonstrate the use of phase images for holographic data storage. Use of phase images as input leads to uniform diffraction efficiency of multiplexed data pages. Use of binary phase-based data pages with 0 and p phase changes produces uniform spectral distribution at the Fourier plane. This in turn facilitates better recording of higher spatial frequencies. We experimentally demo...
متن کامل