/unilm

UniLM - Unified Language Model Pre-training / Pre-training for NLP and Beyond

Primary LanguagePythonMIT LicenseMIT

UniLM

We develop pre-trained models for natural language understanding (NLU) and generation (NLG) tasks

The family of UniLM:

UniLM: unified pre-training for language understanding and generation

MiniLM (new): small pre-trained models for language understanding and generation

LayoutLM (new): multimodal (text + layout/format + image) pre-training for document understanding (e.g. scanned documents, PDF, etc.)

s2s-ft (new): sequence-to-sequence fine-tuning toolkit

News

Release

***** New February, 2020: UniLM v2 | MiniLM v1 | LayoutLM v1 | s2s-ft v1 release *****

***** October 1st, 2019: UniLM v1 release *****

License

This project is licensed under the license found in the LICENSE file in the root directory of this source tree. Portions of the source code are based on the transformers project.

Microsoft Open Source Code of Conduct

Contact Information

For help or issues using UniLM, please submit a GitHub issue.

For other communications related to UniLM, please contact Li Dong (lidong1@microsoft.com), Furu Wei (fuwei@microsoft.com).