Interpreting the prediction process of a deep network constructed from supervised topic models

Jianshu Chen, Ji He, Xiaodong He, Lin Xiao, Jianfeng Gao, Li Deng

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

In this paper, we propose an approach to interpret the prediction process of the BP-sLDA model, which is a supervised Latent Dirichlet Allocation model trained by Back Propagation over a deep architecture. The model is shown to achieve state-of-the-art prediction performance on several large-scale text analysis tasks. To interpret the prediction process of the model, often demanded by business data analytics applications, we perform evidence analysis on each pair-wise decision boundary over the topic distribution space, which is decomposed into a positive and a negative components. Then, for each element in the current document, a novel evidence score is defined by exploiting this topic decomposition and the generative nature of LDA. Then the score is used to rank the relative evidence of each element for the effectiveness of model prediction. We demonstrate the effectiveness of the method on a large-scale binary classification task on a corporate proprietary dataset with business-centric applications.

Original languageEnglish
Title of host publication2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2429-2433
Number of pages5
ISBN (Electronic)9781479999880
DOIs
StatePublished - May 18 2016
Externally publishedYes
Event41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Shanghai, China
Duration: Mar 20 2016Mar 25 2016

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2016-May
ISSN (Print)1520-6149

Conference

Conference41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016
Country/TerritoryChina
CityShanghai
Period03/20/1603/25/16

Keywords

  • BP-sLDA
  • Topic model
  • back propagation
  • deep architecture
  • mirror descent

Fingerprint

Dive into the research topics of 'Interpreting the prediction process of a deep network constructed from supervised topic models'. Together they form a unique fingerprint.

Cite this