Abstract

Probabilistic topic models in low data resource scenarios are faced with less reliable estimates due to sparsity of discrete word co-occurrence counts, and do not have the luxury of retraining word or topic embeddings using neural methods. In this challenging resource constrained setting, we explore mixture models which interpolate between the discrete and continuous topic-word distributions that utilise pre-trained embeddings to improve topic coherence. We introduce an automatic trade-off between the discrete and continuous representations via an adaptive mixture coefficient, which places greater weight on the discrete representation when the corpus statistics are more reliable. The adaptive mixture coefficient takes into account global corpus statistics, and the uncertainty in each topic’s continuous distributions. Our approach outperforms the fully discrete, fully continuous, and static mixture model on topic coherence in low resource settings. We additionally demonstrate the generalisability of our method by extending it to handle multilingual document collections.

Highlights

  • Background crete categorical and continuousGaussian distribu-2.1 Unsupervised Learning with Latent Dirichlet Allocation (LDA) tions

  • Given the dominance of pre-trained word embeddings in modern NLP, would continuous representations outperform discrete representations even in low resource settings? Surprisingly, we find that discrete LDA outperforms its fully continuous counterpart on topic coherence measures which correlate with human judgement (Lau et al, 2014)

  • Our work proposes an automatic trade-off between externally trained continuous representations and traditional co-occurrence count-based statistics that is specific to each word and topic

Read more

Summary

Introduction

We adopt a mixture model where each word has some probability of either coming from its Discrete LDA (Blei et al, 2003) describes a gen- categorical (discrete) or Gaussian (continuous) diserative probabilistic model of a corpus with la- tribution. The generative process for this model tent topics. We can define a corpus with with K topics is as follows:. D documents and K topics, where each document has a multinomial distribution over topics, Θ = {θ1, · · · , θD}, and each topic has a multinomial distribution over words, Φ = {φ1, · · · , φK}. Θ and Φ are the set of document-topic and topic-.

Objectives
Results
Conclusion

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.