Jupyter notebook that demonstrates how to make a recommender system with courses in Chulalongkorn unversity
-
Updated
Dec 21, 2021 - Jupyter Notebook
#
sentence-embeddings
Here are 7 public repositories matching this topic...
Embedding based vector/semantic search app for poetry [App and EDA notebooks]
approximate-nearest-neighbor-search semantic-search sentence-embeddings data-enrichment vector-search vllm
-
Updated
Nov 7, 2023 - Jupyter Notebook
The python codes of vue4logs code converted from Ipython notebooks. These codes are used in creating benchmarks.
-
Updated
Mar 24, 2023 - Jupyter Notebook
Multilingual sentence embedding evaluation for Finnish-English course similarity detection. Bachelor's thesis, JAMK 2026. Includes dataset, notebooks, production FastAPI service, and live demo.
python nlp machine-learning sentence-embeddings fastapi finnish-language huggingface multilingual-nlp labse
-
Updated
May 31, 2026 - Jupyter Notebook
Fine-tune BERT for biomedical sentence embeddings: unsupervised TSDAE domain adaptation on PubMed abstracts, then SBERT fine-tuning on NLI. Compares 4 models on PubMed retrieval, NanoBEIR (SciFact, NFCorpus, SCIDOCS) and STSb. Colab notebook included.
nlp information-retrieval pubmed supervised-learning unsupervised-learning domain-adaptation sentence-embeddings fine-tuning sentence-transformers sbert tsdae biomedical-nlp
-
Updated
Oct 12, 2026 - Jupyter Notebook
An end-to-end semantic search pipeline on 568K+ Amazon reviews: TF-IDF baseline, Sentence-Transformer embeddings, a scalable FAISS index, UMAP visualization, and an honest look at where embeddings fail. Built as both a reusable reference and a teaching notebook.
nlp machine-learning information-retrieval deep-learning semantic-search nlp-machine-learning sentence-similarity sentence-embeddings amazonreviews faiss mlops sentence-transformers amazonreviewdataset faiss-vector-database faiss-similarity
-
Updated
Sep 24, 2026 - Jupyter Notebook
Workshop notebooks (Bern, 2026) on deriving subject metadata from early modern Bernese normative texts (Policeyordnungen, 1528–1798). Part I (HISTMET) tests whether unsupervised clustering recovers subjects and how text length affects this; Part II introduces automated subject indexing with Annif. Runs in Google Colab.
clustering digital-humanities skos sentence-embeddings subject-indexing legal-history google-colab annif early-modern-history
-
Updated
Oct 24, 2026 - Jupyter Notebook
Add this topic to your repo
To associate your repository with the sentence-embeddings topic, visit your repo's landing page and select "manage topics."