Distributional Statistics / Semantic Models
Early work assessing high-dimensional semantic models such as HAL and LSA, and what they explain about meaning.
Much of my early undergraduate training was on assessing high dimensional semantic models like HAL (Hyperspace Analogue to Language) and LSA (Latent Semantic Models). I have not lost any of my early appreciation for their explanatory power.
Selected papers
- Willits, J. A., D’Mello, S. K., Duran, N. D., & Olney, A. (2007). Distributional statistics and thematic role relationships. Proceedings of the 29th Annual Conference of the Cognitive Science Society. [PDF]
- Bellissens, C., Jeuniaux, P., Duran, N. D., & McNamara, D. S. (2010). A text relatedness and dependency computational model. Studia Informatica Universalis, 8, 127–153. [PDF]
- Dale, R., Duran, N. D., & Morehead, J. R. (2012). Prediction during statistical learning, and implications for the implicit/explicit divide. Advances in Cognitive Psychology, 8, 196–209. [PDF]
- Duran, N. D., & Dale, R. (2009). Predictive arm placement in the statistical learning of position sequences. Proceedings of the 31st Annual Conference of the Cognitive Science Society. [PDF]
See the full list on the publications page.