Representing Inferences and their Lexicalization

TL;DR

This paper introduces a novel computational architecture for representing inferences in natural language understanding, focusing on how words contribute to evolving situational meaning and inference during text processing.

Contribution

It presents a new approach to modeling inferences and lexicalization in natural language understanding, with an implemented architecture demonstrating feasibility.

Findings

Successfully developed a computational architecture for inference representation

Implemented the architecture on real text data

Proved the feasibility of the proposed design

Abstract

We have recently begun a project to develop a more effective and efficient way to marshal inferences from background knowledge to facilitate deep natural language understanding. The meaning of a word is taken to be the entities, predications, presuppositions, and potential inferences that it adds to an ongoing situation. As words compose, the minimal model in the situation evolves to limit and direct inference. At this point we have developed our computational architecture and implemented it on real text. Our focus has been on proving the feasibility of our design.