Table 2 General NLP-related tags
Category | Tags |
|---|---|
Data type | D1: All patient related records |
D2: Clinical studies | |
D3: Registry data | |
D4: Protein data | |
D5: Genome data | |
D6: Forum posts, chatlogs, social media | |
D7: Speech data, dialogue data | |
D8: Image data | |
D9: Knowledge graph, thesaurus | |
D10: Medical online information (Wikipedia, drug information, FAQs, etc.) | |
D11: Patents | |
D12: News articles and press releases | |
D13: Clinical guidelines | |
Data language | free text, e.g. English, German |
Task | T1: Classification |
T2: Information extraction | |
T3: Clustering | |
T4: Text generation | |
T5: Embeddings/representations | |
T6: New dataset creation | |
T7: Question answering | |
T8: Text summarization | |
T9: Translation | |
T10: Reinforcement learning | |
T11: Recommender system | |
T12: Natural Language Inference and entailment | |
T13: Topic model | |
T14: Probing | |
T15: Ranking | |
Secondary task | S1: Explainability |
S2: Domain adaptation | |
S3: Bias, fairness | |
S4: Resource-awareness | |
Model type | M1: Transformer-variants (BERT, RoBERTa etc.) |
M2: Convolutional Neural Nets (CNNs) | |
M3: Recurrent Neural Nets (RNN, LSTM) | |
M4: Statistical models (Bayes, conditional probabilities, CRF) | |
M5: Graph Neural Networks (GNNs) | |
M6: Dimension reduction | |
M7: Graphical models (PGM) | |
M8: Generative Adversarial Networks (GANs) | |
M9: Rule-based models | |
M10: Decision trees, Random Forest | |
M11: Support Vector Machines (SVM) | |
M12: K-nearest neighbors (kNN) | |
M13: Pointer generator model | |
M14: Feedforward neural network | |
M15: Logistic regression | |
M16: Linear regression | |
No contribution |