The paper describes a new method of constructing semantic expansions of search requests for improving the results of Web search. This method is based on the theory of K-representations a new theory of designing semantic-syntactic analyzers of natural language texts with the broad use of formal means for representing input, intermediary, and output data. The current version of the theory is set ...

The Olympics-oriented mobile game news ordering system introduced in the paper involved the technology of natural language processing, machine learning and information extraction. We collected text information from the major Internet media websites about the table-tennis and badminton games of the 2004 Athens Olympics; then we transformed these texts information into structured data through inf...

1) What function does Theme perform in written workplace texts? After an initial analysis of the data, subsequent and more focused questions were developed. These more specific questions were theoretically oriented and focused primarily on identifying the boundary between Theme and Rheme, and the issues arising from decisions in this respect. A discussion of these questions, providing the theor...

The paper discusses some aspects of a work in progress aimed at the development of technologies for digitization of Bulgarian folk music and building a digital library with Bulgarian folk songs presented with their music, texts and notes. This library provides digital preservation of the sound recordings, lyrics and notations of more than 1000 Bulgarian folk songs and tools for various types of...

We report on a head-driven way to generate a languagespecific representation for a language-independent conceptual structure. With a grammar oriented towards conceptual rather than phrasal structure, the approach shows some advant~ages over previous works in headdriven generation. ~It is particularly suited for multilingual generation systems where language-independent representations andlproce...

The purpose of this study is to develop a plausible method to code and compile Buddhist texts from original Tibetan scripts into Romanized form. Using GUI (Graphical User Interface) based on Object Oriented Design, a dictionary of Tibetan characters can be easily made for Buddhist literature researchers. It is hoped that a computer system capable of highly accurate character recognition will be...

In this paper, we introduce text polishing, a novel, surface-oriented approach to using revisions in natural language generation in order to improve the fluency of generated texts. In this approach, markupbased revision rules are used to implement sentence planning operations such as aggregation, referring expression generation and discourse marker insertion. By working close to the surface, we...

This paper presents a systematic approach to implementing fuzzy parsers. A fuzzy parser is a form of syntax analyzer that performs analysis on selected portions of its input rather than performing a detailed analysis of a complete source text. Fuzzy parsers are often components of software tools and also of program development environments that extract information from source texts. This paper ...

The latest in a series of natural language processing system evaluations was concluded in October 1995 and was the topic of the Sixth Message Understanding Conference (MUC-6) in November, co-chaired by Ralph Grishman (NYU) and Beth Sundheim (NRaD). Participants were invited to enter their systems in as many as four different task-oriented evaluations. The Named Entity and Coreference tasks enta...

Despite human-centered approaches to the development of electronic text, the visually impaired remain particularly susceptible to oversight. The digital realm has a strong bias toward visually-oriented representation, and is generally unaware of accessibility issues. To overcome this potential digital divide, efforts are underway in the development of both assistive reading technologies and acc...