University of Cambridge > > Natural Language Processing Reading Group > NLP Reading Group: Cross-Cutting Models of Lexical Semantics

NLP Reading Group: Cross-Cutting Models of Lexical Semantics

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Jimme Jardine.

@article{reisinger2003cross, title={Cross-Cutting Models of Lexical Semantics}, author={Reisinger, J. and Mooney, R.}, journal={Journal of Artificial Intelligence Research}, volume={18}, pages={1—44}, year={2003} }

Context-dependent word similarity can be measured over multiple cross-cutting dimensions. For example, lung and breath are similar thematically, while authoritative and superficial occur in similar syntactic contexts, but share little semantic similarity. Both of these notions of similarity play a role in determining word meaning, and hence lexical semantic models must take them both into account. Towards this end, we develop a novel model, Multi-View Mixture (MVM), that represents words as multiple overlapping clusterings. MVM finds multiple data partitions based on different subsets of features, subject to the marginal constraint that feature subsets are distributed according to Latent Dirichlet Allocation. Intuitively, this constraint favors feature partitions that have coherent topical semantics. Furthermore, MVM uses soft feature assignment, hence the contribution of each data point to each clustering view is variable, isolating the impact of data only to views where they assign the most features. Through a series of experiments, we demonstrate the utility of MVM as an inductive bias for capturing relations between words that are intuitive to humans, outperforming related models such as Latent Dirichlet Allocation.

This talk is part of the Natural Language Processing Reading Group series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2024, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity