A Comparative Study of Pretrained Language Models on Thai Social Text Categorization.
Thanapapas HorsuwanKasidis KanwatcharaPeerapon VateekulBoonserm KijsirikulPublished in: CoRR (2019)
Keyphrases
- text categorization
- language model
- language modeling
- n gram
- text classification
- document retrieval
- probabilistic model
- retrieval model
- information retrieval
- knn
- feature selection
- word segmentation
- query expansion
- multi label
- naive bayes
- text documents
- test collection
- text classifiers
- term weighting
- query terms
- cross language
- k nearest neighbor
- term frequency
- semi supervised learning
- pseudo relevance feedback
- text collections
- translation model
- retrieval effectiveness
- information extraction
- vector space model
- document representation
- similarity measure