-
What: WordPiece is an unsupervised multi-lingual text tokenizer. It is used in models such as BERT, though can in principle be used for many NLP models. It produces a user-specified fixed-size vocabul…
-
Our brains are amazing at converting sequences of syllables into words. Finding the gaps between them.
Experiment: First, convert bodies of text into phonemes, possibly using this dictionary: http://…
-
Hi!
I would like to try something new using your code for unsupervised training, but currently cannot find network.mesh while training.
Could you provide something about how to use it? It will be …
-
After reading your great work:
> GLoMo: Unsupervisedly Learned Relational Graphs as Transferable Representations
I've noticed that in the paper you mentioned that the code was removed for review.…
-
I would like to learn word vectors in an unsupervised fashion using a large corpus. I am trying to understand a bit how the `lrUpdateRate` parameter works. It appears to play the role of a learning ra…
-
I have this conceptual doubt in the part where we are obtaining word level representations from characters using the final output of BiLSTM network. We are initializing the character embeddings using …
-
Hi,
Thank you for the repo and the youtube explanation. I am trying out dimensionality reduction for an unsupervised document similarity task. I tried to reproduce your dimensionality reduction meth…
-
Hi,
I am trying to run the pre-trained system and get the labels but I got an error below:
```
>>> python get_labels.py -cg -us -s
Extracting candidate labels
/usr/local/lib/python3.6/site-pa…
-
There are already some open issues regarding the paired image to image translation task. I am also interested in this. The authors present also comparisons with improved pix2pixHD variants such as p…
-
What you'll learn:
- Would it be better to drop the reference to cosine similarity here as an "unsupervised method" along the lines of tf-idf and topic modeling?
- Would "word embedding" be better …