1. preprocessing data :

• data/raw -> data_loader.py -> text_cleaner.py -> tokenizer.py -> pos_tagger.py -> stopwords_remover.py -> Store in data/processed/

2. Embedding

• data/processed -> embeddings/[phobert|sgns|ppmi_svd]_embedder.py -> qdrant_client.py -> Store in dtaa/embeddings/

3. Clustering and analyzwe

• data/embeddings/ -> clustering/[kmeans|dbscan]_clusterer.py -> clustering/cluster_analyzer.py -> Store in data/clusters/

4. aligner

• data/clusters/ -> alignment/procrustes_aligner.py -> alignment/temporal_mapper.py -> Store in data/alignments/

5. change in ngữ nghĩa

• data/alignments/ -> semantic_change/change_detector.py -> semantic_change/cosine_calculator.py → semantic_change/context_analyzer.py -> semantic_change/social_event_mapper.py → Store in outputs/results/

..... tren day chi la tham khao