#BERT
2 related articles
·1 min
Predicting Party Affiliation with BERT: A New Approach to Analyzing Austrian Parliamentary Speeches
This article introduces a new study based on a fine-tuned BERT model that predicts party affiliation in Austrian parliamentary speeches to analyze convergence and divergence in party speech styles, and releases a 1996-2018 prediction dataset.
Read more →
·2 min
BERT Tokenization Bottleneck Moves Upstream: Normalization Swallows 88% of Encoding Time
BERT tokenization profiling reveals normalization consumes 88% of English encoding time, WordPiece only 8%. Inside Simon Brandeis's optimization: SIMD skips ASCII, page cache speeds non-ASCII scripts, and why to measure tokenization separately in RAG and embedding services.
Read more →