Nominal Compound Interpretation by Intelligent Agents

Marjorie McShane, Stephen Beale, Petr Babkin

Abstract


This paper presents a cognitively-inspired algorithm for the semantic analysis of nominal compounds by intelligent agents. The agents, modeled within the OntoAgent environment, are tasked to compute a full context-sensitive semantic interpretation of each compound using a battery of engines that rely on a high-quality computational lexicon and ontology. Rather than being treated as an isolated "task", as in many NLP approaches, nominal compound analysis in OntoAgent represents a minimal extension to the core process of semantic analysis. We hypothesize that seeking similarities across language analysis tasks reflects the spirit of how people approach language interpretation, and that this approach will make feasible the long-term development of truly sophisticated, human-like intelligent agents. The initial evaluation of our approach to nominal interpretation is promising, and suggests one feature of nominal compounds that has been long-recognized by linguists but runs counter to much recent work on machine-learning-oriented approaches to NN analysis: many nominal compounds are fixed expressions, requiring individual semantic specification at the lexical level.

Keywords


nominal compounds; NN compounds

Full Text:

PDF

Refbacks

  • There are currently no refbacks.