UTCS Artificial Intelligence
Distributional semantics, multimodal models, bayesian methods.
roller [at] cs utexas edu
Representing Meaning with a Combination of Logical Form and Vectors
Islam Beltagy, Stephen Roller, Pengxiang Cheng, Katrin Erk, and Raymond J. Mooney,
arXiv preprint arXiv:1505.06816 [cs.CL]
Inclusive yet Selective: Supervised Distributional Hypernymy Detection
Stephen Roller, Katrin Erk, and Gemma Boleda, In
Proceedings of the 25th International Conference on Computational Linguistics (COLING 2014)
, pp. 1025--1036, Dublin, Ireland, August 2014.
UTexas: Natural Language Semantics using Distributional Semantics and Probabilistic Logic
Islam Beltagy, Stephen Roller, Gemma Boleda, and Katrin Erk, and Raymond J. Mooney, In
The 8th Workshop on Semantic Evaluation (SemEval-2014)
, pp. 796--801, Dublin, Ireland, August 2014.
A Multimodal LDA Model Integrating Textual, Cognitive and Visual Modalities
Stephen Roller and Sabine Schulte im Walde, In
Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing (EMNLP 2013)
, pp. 1146--1157, Seattle, WA, October 2013.
Areas of Interest
Combining Logical and Distributional Semantics
Natural Language Learning
Natural Language Processing
Unsupervised Learning, Clustering, and Self-Organization
Currently affiliated with