Training Agents to Recognize Text by Example

Publisher Summary An important function of an agent is to be “on the lookout” for bits of information that are interesting to its user, even if these items appear in the midst of a larger body of unstructured information. The question is to decide which of these agents are meaningful and what is to be done with the result. Especially when agents are used to recognize text, parsers that require input in the form of textual grammar rules usually drive them. Editing grammar is difficult and error-prone for end users. Grammex (Grammars by Example) is the first direct manipulation interface designed to allow non-expert users to define grammars interactively. The user presents concrete examples of text that he or she would like the agent to recognize. An iterative process, in which Grammex heuristically parses the example and displays a set of hypotheses, constructs rules and the user critiques the system's suggestions. Actions to take upon recognition are also demonstrated by example.