Abstract:
Psycholinguistic theories of semantic memory form the basis of understanding of natural language concepts. These theories are used here as an inspiration for implementing a computational model of semantic memory in the form of semantic network. Combining this network with a vector-based object-relation-feature value representation of concepts that includes also weights for confidence and support, allows for recognition of concepts by referring to their features, enabling a semantic search algorithm. This algorithm has been used for word games, in particular the 20-question game in which the program tries to guess a concept that a human player thinks about. The game facilitates lexical knowledge validation and acquisition through the interaction with humans via supervised dialog templates. The elementary linguistic competencies of the proposed model have been evaluated assessing how well it can represent the meaning of linguistic concepts. To study properties of information retrieval based on this type of semantic representation in contexts derived from on-going dialogs experiments in limited domains have been performed. Several similarity measures have been used to compare the completeness of knowledge retrieved automatically and corrected through active dialogs to a “golden standard”. Comparison of semantic search with human performance has been made in a series of 20-question games. On average results achieved by human players were better than those obtained by semantic search, but not by a wide margin.