OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Models

Nested Ner TACL2020 Transformers

Nested Ner TACL2020 Transformers is a Python implementation for preparing data and training BERT-based models for nested named-entity recognition, with documented experiment workflows for ACE-2004, ACE-2005 and GENIA.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Nested Ner TACL2020 Transformers — OpenViST project profile in AI Models.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when working with Python research code and seeking a documented route from supported corpus data to nested NER training.

Who it is for

  • Researchers reproducing nested NER experiments on the named corpora.
  • Developers building a corpus-preparation and model-training workflow for nested entity recognition.

Documented uses

  • Generate processed training files from sample data.
  • Parse and prepare ACE-2004, ACE-2005 or GENIA corpus data.
  • Start training a nested NER model with the repository's training script.
Before you choose

Requirements & limits

  • The repository documents a specific tested dependency stack: Python 3.7, PyTorch 1.10.0, NumPy 1.17.3, StanfordNLP 0.2.0 with Java CoreNLP Server 3.9.2, and Transformers 4.12.0.
  • ACE-2004 and ACE-2005 workflows require the corresponding corpus and an additional mention-extraction archive; GENIA uses its own corpus parser.
  • Model and training settings are configured in config.py.
  • The repository lists a GPL-3.0 license.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Prepare sample data and start training

Generate the repository's sample processed data and begin the documented training workflow.

Before you start

  • Python 3.7
  • PyTorch 1.10.0
  • NumPy 1.17.3
  • StanfordNLP 0.2.0 and Java Stanford CoreNLP Server 3.9.2
  • Transformers 4.12.0

Steps

  1. Run the command below to create processed files in ./data/.

    Documented command
    python gen_data.py

  2. Run the command below to start training.

    Documented command
    python train.py

Expected outcome

Processed sample data is generated and the training script is started.

Guide limitations

  • The README does not specify sample dataset contents or a resulting model-evaluation procedure.
Documentation 1 ↗
Source-based practical guide

Prepare and train on GENIA

Follow the documented GENIA corpus preparation and training sequence.

Before you start

  • The GENIA corpus placed in ../GENIA/.
  • The Python, PyTorch, NumPy, StanfordNLP/CoreNLP Server and Transformers versions listed by the repository.

Steps

  1. Run the command below to extract sentences into ./data/genia/.

    Documented command
    python parse_genia.py

  2. Run the command below to prepare processed files in ./data/.

    Documented command
    python gen_data_for_genia.py

  3. Run the command below to start training.

    Documented command
    python train.py

Expected outcome

GENIA data is parsed and prepared before the training script is started.

Guide limitations

  • The instructions do not give evaluation steps or describe results produced after training.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
yahshibu/nested-ner-tacl2020-transformers · Official homepage title · retained in its source language
How we review sourcesSuggest a correction