This section gives you ideas about the kind of tasks you can use Rubrix for. It also describes some of the tasks on our roadmap, if there's some task you want and don't see here or you want to contribute a task, file an issue or use the Discussion forum at Rubrix's GitHub page.
According to the amazing NLP Progress resource by Seb Ruder:
Rubrix is flexible with input and output shapes, which means you can model many related tasks like for example:
- Sentiment analysis
- Natural Language Inference
- Relationship Extraction
- Stance detection
- Multi-label text classification
- Node classification in knowledge graphs.
The most well-known task in this category is probably Named Entity Recognition:
Rubrix is flexible with input and output shapes, which means you can model related tasks like for example:
- Named entity recognition
- Part of speech tagging
- Key phrase extraction
- Slot filling
- Text2Text, covering summarization, machine translation, natural language generation, etc.
- Question answering
- Image classification
- Image captioning
- Speech2Text