Merge remote-tracking branch 'origin/master'

Author: nreimers

examples/unsupervised_learning/TSDAE/README.md

@@ -1,9 +1,9 @@
 # TSDAE
 
-This folder shows an example, how can we train an unsupervised [TSDAE (Tranformer-based Denoising AutoEncoder)](https://arxiv.org/abs/2104.06979) model with pure sentences as training data.
+This section shows an example, of how we can train an unsupervised [TSDAE (Tranformer-based Denoising AutoEncoder)](https://arxiv.org/abs/2104.06979) model with pure sentences as training data.
 
 ## Background 
-During training, TSDAE encodes damaged sentences into fixed-sized vectors and requires the decoder to recon-struct  the  original  sentences  from  this  sentenceembeddings. For good reconstruction quality, thesemantics must be captured well in the sentenceembeddings from the encoder. Later, at inference,we only use the encoder for creating sentence embeddings. The architecture is illustrated in the figure below:
+During training, TSDAE encodes damaged sentences into fixed-sized vectors and requires the decoder to reconstruct the original sentences from these sentenceembeddings. For good reconstruction quality, thesemantics must be captured well in the sentenceembeddings from the encoder. Later, at inference,we only use the encoder for creating sentence embeddings. The architecture is illustrated in the figure below:
 
 ![](https://raw.githubusercontent.com/UKPLab/sentence-transformers/master/docs/img/TSDAE.png)
 
@@ -89,4 +89,4 @@ If you use the code for augmented sbert, feel free to cite our publication [TSDA
     year = "2021",
     url = "https://arxiv.org/abs/2104.06979",
 }
-```
+```