Transformer-based Denoising AutoEncoder for Sentence Transformers Unsupervised pre-training.
-
Updated
Nov 17, 2025 - Python
Transformer-based Denoising AutoEncoder for Sentence Transformers Unsupervised pre-training.
AI-based classification of BIM elements using sentence embeddings and bSDD
Domain adaption for an embedding model using unsupervised and supervised finetuning on scientific texts for the SciFact retrieval task.
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.
IITK at SemEval Task 1: Semantic Textual Relatedness for African and Asian Languages
To associate your repository with the tsdae topic, visit your repo's landing page and select "manage topics."