Skip to content
#

seqeval

Here are 7 public repositories matching this topic...

Language: All
Filter by language

End-to-end NLP experiments for movie-genre prediction from plot summaries in English & Persian—covering document-level baselines, BERT fine-tuning, and NER+LSTM-CRF pipelines, with datasets and evaluation code.

  • Updated Oct 6, 2025
  • Jupyter Notebook

An end-to-end comparative study on Named Entity Recognition (NER) benchmark datasets. This project explores the progression from scratch-built deep learning sequence models (LSTM, BiLSTM, BiLSTM-CRF) to state-of-the-art transformer fine-tuning (DistilBERT). Includes subword-label alignment, strict evaluation using seqeval, and an interactive Gradio

  • Updated Jul 22, 2026
  • Jupyter Notebook

This repo explores token classification for abbreviation and long-form detection using RoBERTa. We evaluate the impact of adding 50% of the PLODv2-filtered dataset, achieving improved F1 and recall. The repo includes methodology, evaluation using seqeval, and confusion matrix analysis.

  • Updated Jun 7, 2025
  • Python

Add this topic to your repo

To associate your repository with the seqeval topic, visit your repo's landing page and select "manage topics."

Learn more