Natural Language Generation Essay -- Computer Science

Natural Language Generation Abstract Natural language generation is a relatively new field in computer science. The two main questions to be solved are "what to say" and "how to say it." What to say includes answering questions not specifically asked by the user, and remembering previous statements made by the user and by the program itself. How to say it involves construction of logical sentences, use of pronouns, and sentence fragments. When speech synthesis is used, it also involves producing intelligible word rhythm, emphasis, and pauses. A new, exciting extension of speech synthesis is the inclusion of "emotion" in speech. User: ELIZA: Men are all alike In what way? They’re always bugging us about something or other Can you think of a specific example? Well, my boyfriend made me come here. Your boyfriend made you come here. He says I’m depressed much of the time. I am sorry to hear you are depressed. It’s true, I am unhappy. Do you think coming here will help you not be unhappy? I need some help; that much seems certain. What would it mean to you if you got some help? Perhaps I could get along with my mother. Tell me more about your family. My mother takes care of me. Who else in your family takes care of you? My father. Your father. You are like my father in some ways. What resemblance do you see? Natural language generation is the generation of printed text as well as synthesized speech. The transcript above is from a system that generates "psychoanalytic" responses to user input. This system is called ELIZA, and was developed at MIT in the 1960s. The program illustrates some of the issues of natur... ...gories such as pitch, voice speed, loudness, and pause length. She wrote a program that output these changes based on the emotion that it was asked to portray. Sample output from this program can be found online. When "emotion" can be output regularly in speech synthesis, a new breed of natural language applications will begin! Natural language generation is a young and exciting subject. There is still much research to be done to find the best way of representing a grammar, and providing a program capable of remembering previous statements, interpreting user input, speaking in sentences and sentence fragments, and providing a "natural" conversation. Even newer is the possibility of adding "emotional flavor" to synthesized speech. The windows that are opened by these studies present such a vast landscape of new applications that it is impossible to imagine them all.