A “natural logic” for natural language processing and knowledge representation
Syed Shamsher Ali · 1994
We define a knowledge representation and inference formalism that is well suited to language processing. In this formalism every subformula of a formula is closed. We motivate this by observing that any formal language with (potentially) open sentences is an inappropriate medium for the representation of language sentences. Open sentences in such languages are a consequence of the separation of variables from their quantifier and type constraints, typically in the antecedents of rules. This is inconsistent with the use of descriptions and noun phrases corresponding to variables in language. Variables in language are constructions that are typed and quantified as they are used. A consequence of this is that variables in language may be freely reused in dialog. This leads to the use of pronouns and discourse phenomena such as ellipsis involving reuse of entire subformulas. We present an augmentation to the representation of variables so that variables are not atomic terms. These variables are typed and quantified as they are defined and used. This leads to an extended, more natural logical language whose use and representations are consistent with the use of variables in language. Structured variables simplify the tasks associated with language processing and generation, by localizing noun phrase processing. The formalism is defined in terms of a propositional semantic network, starting from nodes and arcs connecting nodes, subsumption, matching, to inference. It allows the resolution of some representational difficulties with certain classes of language sentences (e.g. the so-called donkey sentences and sentences involving branching quantifiers). Reuse phenomena, such as pronominalization and ellipsis, are captured in the representation by structure-sharing. A major advantage of this structured representation of variables is that it allows a form of terminological and derived subsumption similar to surface reasoning in language.