Computational Linguistics Colloquium
Thursday, 3 July 2014, 16:15
Conference Room, Building C7.4
Sense Learning with Topic Modelling
Timothy BaldwinDept of Computing and Information Systems
University of Melbourne, Australia
In this talk, I will describe an unsupervised topic modelling approach to automatically induce word senses of a target word, and describe how the method can be applied to predominant sense learning and sense frequency estimation, and also the novel tasks of detecting senses which are not attested in the corpus, and identifying novel senses in the corpus which are not captured in the sense inventory.
If you would like to meet with the speaker, please contact
Tim Baldwin.