tsdae VS HyperGAN

A new PyPI package for training sentence embedding models in just 2 lines.

The acquisition of sentence embeddings often necessitates a substantial volume of labeled data. However, in many cases and fields, labeled data is rarely accessible, and the procurement of such data is costly. In this project, we employ an unsupervised process grounded in pre-trained Transformers-based Sequential Denoising Auto-Encoder (TSDAE), introduced by the Ubiquitous Knowledge Processing Lab of Darmstadt, which can realize a performance level reaching 93.1% of in-domain supervised methodologies.

The TSDAE schema comprises two components: an encoder and a decoder. Throughout the training process, TSDAE translates tainted sentences into uniform-sized vectors, necessitating the decoder to reconstruct the original sentences utilizing this sentence embedding. For good reconstruction quality, the semantics must be captured well in the sentence embeddings from the encoder. Subsequently, during inference, the encoder is solely utilized to form sentence embeddings.

GitHub : https://github.com/louisbrulenaudet/tsdae

Installation :

And then there's software already prebaked that can do it, but its really taxing on a pc, its called hyperGAN.

There is something called HyperGAN which builds generative adversarial networks (GANs) and those networks take some images as input and give those as output. Here is the GitHub page for that.