This folder contains examples and best practices, written in Jupyter notebooks, for building Natural Language Processing systems for the following scenarios.
| Category | Applications | Methods | Languages |
|---|---|---|---|
| Text Classification | Topic Classification | BERT | en |
| Named Entity Recognition | Wikipedia NER | BERT | en |
| Entailment | MultiNLI Natural Language Inference | BERT | en |
| Question Answering | SQuAD | BiDAF, BERT | en |
| Sentence Similarity | STS Benchmark | Representation: TF-IDF, Word Embeddings, Doc Embeddings Metrics: Cosine Similarity, Word Mover's Distance Models: BERT, GenSen |
|
| Embeddings | Custom Embeddings Training | Word2Vec, fastText, GloVe | |
| Annotation | Text Annotation | Doccano | |
| Model Explainability | DNN Layer Explanation | DUUDNM (Guan et al.) |