Overview
Topic status: We're looking for students to study this topic.
When presented with the word 'bat', what's the first word you think of? This is the basis of human free association memory experiments. The University of South Florida has collected free association data on thousands of words and using thousands of subjects. This data allows the inter-subjective human mental lexicon to be mapped out as a large network structure of words, where the directed edges represent free association probabilities. Such a network can be exploited by technology in a variety of ways, e.g., to enhance information retrieval. Nowadays there are large collections of electronic text available and various models, which allow associations between words to be computed using such collections.
Suits: IT student with a background in programming.
Hypothesis: This project assumes that computational methods for computing word associations may be replicated using corpus based techniques.
Approaches:
- Design and implementation of a number of techniques for computing word associations
- Empirical evaluation of these techniques against the University of South Florida word association norms
References: Nelson, D., McEvoy, C and Screiber, T.A. (2004) The University of South Florida, word association, rhyme and word fragment norms. Behaviour Research Methods, Instruments & Computers, vol. 36, no. 3, pp. 408-420
- Study level
- Honours
- Supervisors
- QUT
- Organisational unit
Science and Engineering Faculty
- Research area
- Contact
-
Please contact the supervisor.
Professor Peter Bruza
Dr Laurianne Sitbon
