Pinned Repositories
ajitrajasekharan.github.io
This is a log of what I learn and work I have done that yielded usable results
bert_mask
This is an example program illustrating BERTs masked language model.
bert_vector_clustering
Clustering learned BERT vectors for downstream tasks like unsupervised NER, unsupervised sentence embeddings etc.
codebook_comparisons
Comparison of codebook vectors of autoencoders (DALLE's dVAE vs VQGAN) that map any image to a fixed vocabulary of vectors
JPTDP_wrapper
A http interface wrapper around Dat Quoc Nguyen's Joint POS tagging and Dependency parser.
multi_gpu_test
Scripts to set up an nvidia GPU machine (ubuntu)
ner_bio_phi_for_phrases
This is a tweaked version of self-supervised NER for tagging phrases
ner_test
This is a test set to evaluate self-supervised NER. Repository evaluates 11 preprocessed data datasets spanning biomedical domain as well as patient privacy related entities (person,location,organization)
root
Fine-tuned BERT model for POS tagging
unsupervised_NER
Self-supervised NER prototype - updated version (69 entity types - 17 broad entity groups). Uses pretrained BERT models with no fine tuning. State-of-art performance on 3 biomedical datasets
ajitrajasekharan's Repositories
ajitrajasekharan/unsupervised_NER
Self-supervised NER prototype - updated version (69 entity types - 17 broad entity groups). Uses pretrained BERT models with no fine tuning. State-of-art performance on 3 biomedical datasets
ajitrajasekharan/bert_mask
This is an example program illustrating BERTs masked language model.
ajitrajasekharan/bert_vector_clustering
Clustering learned BERT vectors for downstream tasks like unsupervised NER, unsupervised sentence embeddings etc.
ajitrajasekharan/codebook_comparisons
Comparison of codebook vectors of autoencoders (DALLE's dVAE vs VQGAN) that map any image to a fixed vocabulary of vectors
ajitrajasekharan/root
Fine-tuned BERT model for POS tagging
ajitrajasekharan/JPTDP_wrapper
A http interface wrapper around Dat Quoc Nguyen's Joint POS tagging and Dependency parser.
ajitrajasekharan/multi_gpu_test
Scripts to set up an nvidia GPU machine (ubuntu)
ajitrajasekharan/ner_bio_phi_for_phrases
This is a tweaked version of self-supervised NER for tagging phrases
ajitrajasekharan/simple_sbd
Breaks down paragraph into sentences on period char taking into account not breaking on period in numeric sequences and abbreviations
ajitrajasekharan/cls_sentence_representations
ajitrajasekharan/huggingface_finetune_wrapper
Simple wrapper to fine tune and test a BERT model for sentence classificaition
ajitrajasekharan/image_text_redaction
Prototype for image text detection, recognition, and redaction. The models used can detect horizontal print and handwritten text. It cannot detected slanted /curved text etc.
ajitrajasekharan/ner_test
This is a test set to evaluate self-supervised NER. Repository evaluates 11 preprocessed data datasets spanning biomedical domain as well as patient privacy related entities (person,location,organization)
ajitrajasekharan/unsupervised_sentence_representations
ajitrajasekharan/utils
A mixed grab bag of utilities
ajitrajasekharan/ajitrajasekharan.github.io
This is a log of what I learn and work I have done that yielded usable results
ajitrajasekharan/bert_descriptors
BERT's MLM head model exposed as a service
ajitrajasekharan/bert_pretrain_wrapper
ajitrajasekharan/cls_for_ood_detection
For supervised text classification tasks, use of CLS to represent sentence to detect OOD inputs relative to training set. Sentence representations are harvested from a self-supervised model (e.g. BERT)
ajitrajasekharan/dummy
ajitrajasekharan/lapos_server
An existing C++ CRF based POS tagger exposed as a service (suitable for fast POS tagging at scale)
ajitrajasekharan/pretrained_model_evaluation
ajitrajasekharan/simple_tense_detector
This is a simple present/past tense detector of a sentence using DEP-POS tagger