Skip to content

Latest commit

 

History

1 Commit

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 

Repository files navigation

Overview

This study provides empirical evidence for task-aware model selection, showing that architectural design choices — not just parameter count — determine performance across NLP tasks. Our results contradicted several baseline assumptions: ALBERT, despite having only 12M parameters, outperformed larger models on QA, while RoBERTa's 125M parameters proved advantageous for NLI. These findings suggest a practical framework for model selection based on task characteristics rather than model size alone.

Transformer Benchmark: NER, NLI, and QA Tasks

Comparative study of 5 transformer architectures (BERT, DistilBERT, RoBERTa, XLNet, ALBERT) fine-tuned across 3 NLP benchmark tasks.

Results

Model NER (ACC) NLI (ACC) QA (EM)
BERT 98.57% 82.42% 78.70
DistilBERT 98.58% 80.68% 72.89
RoBERTa 99.07% 87.40% 78.34
XLNet 99.11% 86.02% 80.52
ALBERT 98.46% 83.50% 83.28

Key Findings

  • XLNet achieved best NER accuracy (99.11%) and competitive NLI performance
  • ALBERT outperformed all models on QA (83.28 EM) despite having only 12M parameters
  • Higher parameter count favors NLI tasks; embedding factorization benefits QA tasks

Tasks & Datasets

Task Dataset Metric
NER CoNLL-2003 ACC, F1
NLI GLUE MNLI ACC
QA SQuAD EM, F1

Structure

notebooks/ ├── ner.ipynb ├── nli.ipynb └── qa.ipynb

Technologies

Python, PyTorch, HuggingFace Transformers, HuggingFace Datasets

About

No description, website, or topics provided.

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages