A Comparative Study of Pretrained Language Models on Thai Social Text Categorization.
Thanapapas HorsuwanKasidis KanwatcharaPeerapon VateekulBoonserm KijsirikulPublished in: ACIIDS (1) (2020)
Keyphrases
- text categorization
- language model
- language modeling
- text classification
- n gram
- feature selection
- knn
- retrieval model
- document retrieval
- multi label
- naive bayes
- probabilistic model
- information retrieval
- text documents
- query expansion
- k nearest neighbor
- word segmentation
- test collection
- semi supervised learning
- text classifiers
- smoothing methods
- term frequency
- document representation
- tf idf
- text collections
- vector space model
- query terms
- active learning
- retrieval effectiveness
- relevance model
- ir models
- unlabeled data