Discriminatively Enhanced Topic Models

This paper proposes a space-efficient, discriminatively enhanced topic model: a V structured topic model with an embedded log-linear component. The discriminative log-linear component reduces the number of parameters to be learnt while outperforming baseline generative models. At the same time, the...

Full description

Saved in:
Bibliographic Details
Main Authors: Chaturvedi, Snigdha, Daume, Hal, Moon, Taesun
Format: Conference Proceeding
Language:English
Subjects:
Bibliographies
Conferences
Context modeling
Convergence
Data mining
Electronic mail
Email
Hidden Markov models
Hybrid power systems
Log linear models
Mathematical model
Platforms
Predictive models
Probabilistic ranking
Ranking
Tasks
Text Mining
Topic Models
Vectors
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper proposes a space-efficient, discriminatively enhanced topic model: a V structured topic model with an embedded log-linear component. The discriminative log-linear component reduces the number of parameters to be learnt while outperforming baseline generative models. At the same time, the explanatory power of the generative component is not compromised. We establish its superiority over a purely generative model by applying it to two different ranking tasks: (a) In the first task, we look at the problem of proposing alternative citations given textual and bibliographic evidence. We solve it as a ranking problem in itself and as a platform for further qualitative analysis of convergence of scientific phenomenon. (b) In the second task we address the problem of ranking potential email recipients based on email content and sender information.
ISSN:1550-4786
2374-8486
DOI:10.1109/ICDM.2013.107