Natural Language Competent Robots

摘要

Why use natural language (NL) to communicate with computer systems? I have always thought the answer was obvious. Since NL is the most natural communication language for people to use [1], it would make computer systems easiest to use if they understood and spoke NL. I often get resistance to this opinion, but the resistance almost always takes the form of comparing current GUIs to current NL interfaces. Current NL interfaces do not work as well as current GUIs, because current computers do not fully understand NL. My feeling is that that just makes NL understanding (NLU) an important research topic. Indeed, not only is NLU in general an active research topic, so is the specific topic of NL interfaces to robots. For example, see the papers in the recent ACM Conference on Human-Robot Interaction [2]. Moreover, not only are people who describe themselves as NLU researchers working at making NL understandable to computers, the field of programming languages can be seen as a bottom-up attack on the same problem. Many advances in programming languages, as far back as the development of assembly languages, have been presented as allowing the programmer to express the problem to be solved in a high-level language that is natural for the human.