Concretion: Assumption-Based Understanding

Concretion: Assumption-Based Understanding Paul S. Jacobs Artificial Intelligence Program GE Research and Development Center Schenectady, NY 12301 USA Abstract A language understanding program must produce as pre- cise a meaning representation as possible from a linguistic input. CONCRETION is the process of developing a specific interpretation by combining various levels of conceptual information. This process represents an assumption-based method of language interpretation, and departs from the traditional approach of treating multiple interpretations as independent. Concretion Mlows the language analyzer to develop a sufficiently specific representation without excessive computation or brittle interpretation rules. 1 Introduction The ambiguity and imprecision of language are the key prob- lems in building language understanding programs. Most sys- tems that perform semantic interpretation [Bobrow and Web- ber, 1980, Sondheimer et al., 1984, Lytinen, 1984, Hirst, 1987] address this imprecision by offering means of selecting among alternative interpretations. The problem with these approaches is that they fail to take into account the interre- lationshiPS among the interpretations, which often support or refute one another to various degrees. A better model is one in which the candidates exist not as distinct choices but as as- sumptions contributing to a complete meaning representation. The language understanding process thus gradually refines a semantic representation based on the support or refutation of each element. For example, consider the following potential inputs: 1. John cut the salami. 2. John gave a kiss to Mary. 3. The investor group seeking control of Warnaco... 4. The ~rm' command takes three arguments. 5. Move back to the last position. The examples above represent potential inputs from sev- eral disparate real and "toy" domains of TRUMP (TRans- portable Understanding Mechanism Package)[Jacobs, 1986b, Jacobs, 1987]. The idea of TRUMP is to use a combination of "core" knowledge about language and certain specialized knowledge to produce a complete semantic interpret~ation. In each of the examples, the italicized word or phrase represents a vague, ambiguous, or metaphorical verb sense. The prob- lem for a good semantic interpreter is to derive the real or intended sense of each phrase without excessive computation or specialized knowledge. For example, the following are rea- sonable paraphrases of a complete semantic interpretation of the above examples: 1. John cut the salami cut =~ sliced (NOT chopped or shortened) 27oi 2. John gave a kiss to Mary gave a kiss ~ kissed (NOT presented) 3. The investor group seeking control of Warnaco... seeking =~ trying (NOT searching) 4. The ~rm' command takes three argmnents. takes ~ requires as input (NOT moves) 5. Move back to the last position. Move back =# return (NOT move backwards) Each of these examples represents a clear, ordinary use of language. Yet a semantic interpreter must use a great deal of knowledge to distinguish the intended sense of the italicized phrase from other related ahd competing senses. It is sim- ply not practical to treat this process as one of discriminating among a large set of distinct interpretations. The space of in- tended meanings is too large, and there are …

Content truncated to 500 words