ABSTRACT
The potential impact of natural language processing (NLP) has been widely recognized since the earliest days of computers. Indeed, even as the first electronic computers were becoming a reality, Alan Turing imagined a symbolic processing system—one with true artificial intelligence—that could converse with a person in a way that could not be distinguished from a conversation one might have with a real person. Turing, in his famous article (1950), called his thought experiment the Imitation Game. Nowadays, it is called the Turing Test. While no computer program has so far come even remotely close to passing the Turing Test for intelligence, and none will be able to do so at any date in the future that we can reasonably predict, NLP programs that do “understand” language—albeit to a far lesser degree than Turing imagined—will be able to perform many useful and valuable tasks for the foreseeable future. Among them are these:
Grammar and style checking—Providing editorial critiques of vocabulary usage, grammar, and style—improving the quality of all sorts of writing—especially the readability of complex technical documents.
Machine translation—Translating texts, especially business and technical texts, from one natural language to another.
Information extraction—Analyzing the meaning of texts in detail, answering specific questions about text content. For many kinds of text (e.g., medical case histories) that are in a well-bounded domain, systems will extract information and put it into databases for statistical analyses.
Natural language interfaces—Understanding natural language commands and taking appropriate actions, providing a much freer interchange between people and computers.
Programming in English—Enabling the use of carefully controlled, yet ordinary, human language to program computers, largely eliminating much of the need for highly-specialized and arcane computer “languages”.
Modeling and simulation—Enabling computer modeling and simulation of all manner of real-world activities and scenarios where symbolic information and symbolic reasoning are essential to success.
