Lapata, Maria

Fountain, Trevor Michael

2013-09-25T13:34:49Z

2013-09-25T13:34:49Z

2013-07-02

The ability to reason about categories and category membership is fundamental to human cognition, and as a result a considerable amount of research has explored the acquisition and modelling of categorical structure from a variety of perspectives. These range from feature norming studies involving adult participants (McRae et al. 2005) to long-term infant behavioural studies (Bornstein and Mash 2010) to modelling experiments involving artificial stimuli (Quinn 1987). In this thesis we focus on the task of natural language categorisation, modelling the cognitively plausible acquisition of semantic categories for nouns based on purely linguistic input. Focusing on natural language categories and linguistic input allows us to make use of the tools of distributional semantics to create high-quality representations of meaning in a fully unsupervised fashion, a property not commonly seen in traditional studies of categorisation. We explore how natural language categories can be represented using distributional models of semantics; we construct concept representations for corpora and evaluate their performance against psychological representations based on human-produced features, and show that distributional models can provide a high-quality substitute for equivalent feature representations. Having shown that corpus-based concept representations can be used to model category structure, we turn our focus to the task of modelling category acquisition and exploring how category structure evolves over time. We identify two key properties necessary for cognitive plausibility in a model of category acquisition, incrementality and non-parametricity, and construct a pair of models designed around these constraints. Both models are based on a graphical representation of semantics in which a category represents a densely connected subgraph. The first model identifies such subgraphs and uses these to extract a flat organisation of concepts into categories; the second uses a generative approach to identify implicit hierarchical structure and extract an hierarchical category organisation. We compare both models against existing methods of identifying category structure in corpora, and find that they outperform their counterparts on a variety of tasks. Furthermore, the incremental nature of our models allows us to predict the structure of categories during formation and thus to more accurately model category acquisition, a task to which batch-trained exemplar and prototype models are poorly suited.

http://hdl.handle.net/1842/7875

en

The University of Edinburgh

Fountain, T. and Lapata, M. (2010). Meaning representation in natural language categorization. In Ohlsson, S. and Catrambone, R., editors, Proceedings of the 31st Annual Conference of the Cognitive Science Society, pages 1916–1921, Portland, Oregon. Cognitive Science Society.

Fountain, T. and Lapata, M. (2011). Incremental models of natural language category acquisition. In Carlson, L., H¨olscher, C., and Shipley, T., editors, Proceedings of the 33rd Annual Conference of the Cognitive Science Society, pages 255–261, Austin, TX, USA. Cognitive Science Society.

Fountain, T. and Lapata, M. (2012). Taxonomy induction using hierarchical random graphs. In Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 466–476, Montr´eal, Canada. Association for Computational Linguistics.

categorisation

cognitive science

Computational linguistics

Modelling the acquisition of natural language categories

Thesis or Dissertation

Doctoral

PhD Doctor of Philosophy