Natural Language and Computer ProgramsAnyone who has tried to explain how a computer, or even a VCR, works to an older relative has a very good idea of ​​why of which the use of natural language is an objective. computer science researchers. Simply put, most people have no desire to learn a computer language to be able to use their electronic devices. In order for users to use computer systems effectively, those systems must be programmed to understand natural language – the language spoken by an ordinary person – and respond in the same way. Most natural language processing systems divide this task into two parts: understanding. and production. Some systems, such as the Ask.com search engine, in which the user types a complete interrogative sentence instead of a few search terms, are programmed to take commands in English and therefore aim for comprehension. Others, particularly those designed to pass the test proposed by Alan Turing in which a computer must perform as a human in conversation with an interrogator, are designed to simply produce realistic responses, sometimes without bothering at all with breaking down the inputs . For simplicity, most natural language programs operate through typed input and printed or on-screen output, since speech recognition and production are just complications at this stage and can always be incorporated later, simply by asking the program to convert speech to text and vice versa. versa. By working only with typed input, many obstacles to understanding are avoided. People, when they speak, have accents, insults, change the structure of sentences mid-thought, stick “like” wherever they want and do many other things that make everyday speech much less simple than the slightly more formal process of typing. However, even typed, an English sentence is not an easy thing to analyze. An example of this difficulty can be seen in the sentence "I left a job for my wife." Out of context, it is impossible to determine which of the two possible meanings is the correct one. Did the speaker quit his job (i.e. quit) because of his wife, or did he quit his job (i.e. did he leave a) for his wife? A computer must be able to refer to the context around such a sentence in order to extract its meaning.