https://github.com/wmkouw/ssa-nlp
Sequential subspace alignment for temporal domain adaptation in natural language processing
https://github.com/wmkouw/ssa-nlp
domain-adaptation natural-language-processing sequential-models subspace-alignment
Last synced: 11 months ago
JSON representation
Sequential subspace alignment for temporal domain adaptation in natural language processing
- Host: GitHub
- URL: https://github.com/wmkouw/ssa-nlp
- Owner: wmkouw
- License: mit
- Created: 2018-10-18T08:59:20.000Z (over 7 years ago)
- Default Branch: master
- Last Pushed: 2019-11-18T19:35:32.000Z (over 6 years ago)
- Last Synced: 2025-03-29T16:22:12.194Z (about 1 year ago)
- Topics: domain-adaptation, natural-language-processing, sequential-models, subspace-alignment
- Language: Jupyter Notebook
- Homepage:
- Size: 43.6 MB
- Stars: 4
- Watchers: 5
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Sequential subspace alignment of word embeddings
This repository contains experiments and visualizations for temporal domain adaptation in the form of semi-supervised subspace alignment for word embeddings. It accompanies the paper
"Back to the future -- Sequential alignment of text representations"
which is to be presented at the AAAI Conference on Artificial Intelligence, 2020 ([preprint](https://arxiv.org/abs/1909.03464)).
Natural Language Processing tasks currently tackled:
- annual paper acceptance prediction
- temporal named entity recognition
- rumour stance and veracity prediction.
### Data
Rumour stance data stems from the EU project [PHEME](https://www.pheme.eu/), which revolves around automatically determining the truth value of online statements. Specifically, we're looking at the journalism use case.
### Contact
Questions and comments can be submitted to the [issues tracker](https://github.com/wmkouw/ssa-nlp/issues).