Automatic Text Analysis

Automatic Text Analysis


(AA), the operation of extracting, from a given text in a natural language, the grammatical and semantic information contained in the text; the operation follows some algorithm in conformity with a description—elaborated in advance—of the particular language. The reverse operation is called automatic text synthesis. Automatic text analysis proceeds in three phases: (1) lexical-morphological—the transition from an individual word form to its lexical and grammatical characteristics; (2) syntactic—the transition to the syntactic structure of a sentence from the chain of lexical and grammatical characteristics representing it; (3) semantic—the transition from the syntactically analyzed sentence to the recording of its meaning. The algorithm of automatic text analysis is usually divided into information about the language (grammar) and information about the process of analysis itself (the “mechanism,” or algorithm proper of the analysis). Automatic text analysis is a necessary phase in different types of automatic processing of texts: automatic translation, automatic reference work, information search, and the like. Automatic text analysis should be distinguished from automatic text research; in the latter information about the language of the text is absent or almost absent, and the text is processed through algorithms with a view to developing a description of the language.


Mel’chuk, I. A. “Morfologicheskii analiz pri mashinnom perevode (preimushchestvenno na materiale russkovo iazyka).” Problemy kibernetiki, issue 6. Moscow, 1961. Pages 207–276.
Dupuis, L. “Un système morphologique . . . .” Information Storage and Retrieval, 1964, vol. 2, no. 1, pp. 29–41.
Mel’chuk, I. A. Avtomaticheskii sintaksicheskii analiz, vol. 1. Novosibirsk, 1964.
Iordanskaia, L. N. Avtomaticheskii sintaksicheskii analiz, vol. 2, Novosibirsk, 1967.
Hays, D. G. Readings in Automatic Language Processing. New York, 1966.
Vauquois, B., G. Veillon, and J. Veyrunes. “Syntax and Interpretation.” Mechanical Translation, 1966, vol. 9, no. 2, pp. 44–54.
Zholkovskii, A. K., N. N. Leont’eva, and Iu. S. Martem’ianov. “O printsipial’nom ispol’zovanii smysla pri mashinnom perevode.” In Mashinnyi perevod, issue 2. Moscow, 1961. Pages 17–46.


References in periodicals archive ?
The remaining five papers review research contributions of SLAIS members over substantial periods of time: Automatic Text Analysis by Artificial Intelligence, Advances in Data Mining for Biomedical Research, Explanation and Reliability of Individual predictions in machine learning, DEX Methodology: Thirty three years of qualitative multi-attribute modeling, and ORANGE: Data Mining Fruitful and Fun.
K|fner, and Boris Egloff of the University of Mainz in Germany used software for automatic text analysis to look for words that relate to sadness (words such as crying and grief), anxiety (worried, fearful), and anger (hate, annoyed).
7 Automatic text analysis for bioinformatics knowledge discovery (Dietrich Rebholz-Schuhmann and Jung-jae Kim)
Automatic text analysis become an integral part of many systems, pushing boundaries of research capabilities towards what one can refer to as an artificial intelligence dream--never ending learning from text aiming at mimicking ways of human learning.
Automatic text analysis can often contribute to understand the text, to gaining knowledge from the data provided in textual form, to realize the underlying facts that have been communicated via the text.
We conclude by providing discussion and some direction for future research on automatic text analysis.
In this way the automatic text analysis is viewed as an information technology of vital importance, because it enables automatic generation of databases with structured patient data that can be explored for improving the diagnostics, care decisions, the personalised treatment of diseases, maintenance of adverse drug events, healthcare management and so on.
Nowadays IE is the common approach to automatic text analysis in biomedicine, but more fundamental research is needed to advance automatic text understanding in principle; there are high expectations that the NLP progress would enable radical improvements in the clinical decision support, biomedical research and the healthcare sphere in general [3].

Full browser ?