The development of natural-language Processing

When the first electronic digital computers were introduced in the late 1940s, their ability to swiftly perform elaborate sequences of calculations--for example, predict the trajectory and control the flight of a rocket--fascinated both specialists and the general public. Their computative abilities, in some respects superhuman, seemed suggestive of human intelligence as the capabilities of no previous machines had been, and early computers (though no faster or more powerful, in fact, than a present-day programmable pocket calculator) were sometimes referred to as "giant electronic brains."

By the 1950s, serious efforts were underway to adapt computers to the task of interpreting ordinary language, or as it was formally called, natural language. A variety of motives, theoretical and practical, lie behind these efforts. On the most theoretical level, natural-language processing was major feature, perhaps the central feature, of artificial

. . .
e up of several words, however; for example, "The pretty redhead ran swiftly down the beach." It was found impractical to try to interpret such a sentence word-by-word; too many words can perform several functions, while sentence structures can vary widely: "Down the beach the pretty redhead swiftly ran." The solution found for natural-language grammars (and applicable to the design of high-level computer-language compilers) was to begin with an overall template, and attempt to apply it to the sentence as a whole by looking for identifying features that allowed words or groups of words to be analysed and interpreted in context (Chafe, 1970). For the above sentences, for example, ran is an unambiguous verb, and attached to it is the adverb swiftly. Beach and redhead are both nouns. But beach (preceded by the article the) directly follows a preposition, allowing down the beach to be identified as a prepositional phrase--and therefore an object, not a subject. Thus, redhead (and its modifying adjective pretty) must be the subject. The problem becomes more complex if the sentence is in the present tense, since runs can also be a noun. In that case, the association of runs with swiftly, an adverb, allows it to be identif
. . .

Some common words found in the essay are:
JUMP Assembler, Lady ELIZA, Kelly Wigg, Conclusion Expert, Noam Chomsky, Conklin Hill, Russian English, Space Odyssey, Romeo Juliet, , natural-language processing, natural language, turing test, computer program, human intelligence, artificial intelligence, expert systems, pretty redhead, natural language processing, assembler language, language processing, translation natural language, conklin hill 1987, kelly wigg 1987, pass turing test,
Approximate Word count = 2628
Approximate Pages = 11 (250 words per page)

More Essays on The development of natural-language Processing