PromCSE
inltk
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
PromCSE
-
State of the Art in Sentence Embeddings
To answer your question about sentence embedding SOTA, it is not s-Bert and hasn't been for a while. SimCSE officially takes the crown since it's been presented at a conference, though according to paperswithcode's benchmark leaderboard there are other papers on arxiv that report higher performance on STS and similar tasks such as DCPCSE. Having tried both of these for my use case I found SimCSE to be better but YMMV.
inltk
-
Which are top APIs for Indian languages mainly VR, OCR, Speech - Text - Speech?
The best tool will vary a little bit from language to language, but your best bets are probably the Indic NLP Library and iNLTK
What are some alternatives?
nlu - 1 line for thousands of State of The Art NLP models in hundreds of languages The fastest and most accurate way to solve text problems.
allennlp - An open-source NLP research library, built on PyTorch.
DiffCSE - Code for the NAACL 2022 long paper "DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings"
SimCSE - [EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821
BERTopic - Leveraging BERT and c-TF-IDF to create easily interpretable topics.
smaller-labse - Applying "Load What You Need: Smaller Versions of Multilingual BERT" to LaBSE
clip-as-service - 🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP
KitanaQA - KitanaQA: Adversarial training and data augmentation for neural question-answering models
ModelNet40-C - Repo for "Benchmarking Robustness of 3D Point Cloud Recognition against Common Corruptions" https://arxiv.org/abs/2201.12296
flair - A very simple framework for state-of-the-art Natural Language Processing (NLP)