-
Adding packages such as fasttext, sent2vec would help to perform NLP Operations in the kernels.
-
I have a little bit better understanding now of the paradigm you are having. It seems that tokenization performance is now much better, and code is much cleaner, excellent work!
Regarding the prep…
-
Hi there,
Currently attempting to launch in docker container.
Been trying to try this out with the unigram model, but am getting silent failures when attempting to load the embedding distributor…
-
Right now I do pretraining for Malaysia language. I got my own dataset collected from wikipedia, social media and public news. Everything is perfect, it just, the loss increasing,
```
I0704 18:35:04…
-
I successfully install the sent2vec python module globally. However, while I tried to predict the vector using the wiki_unigram model, the output is a 600 dim vector with all element 0. Does anyone kn…
-
**Prerequisites**
> Please fill in by replacing `[ ]` with `[x]`.
* [x] Are you running the latest `bert-as-service`?
* [x] Did you follow [the installation](https://github.com/hanxiao/bert-as-…
-
Hi,
I know this is silly problem but I just can't find how to solve this problem.
```
In file included from sent2vec.cpp:315:
./fasttext.h:18:10: fatal error: 'atomic' file not found
#inc…
-
I try to apply the pretrained wikipedia bi-gram model on an existing corpus i have (Simple English wikipedia sentences, tokenized and lowercased with another pipeline). I tried the nnSent command to s…
-
I got 'Model file has wrong file format!'
when using docker:
`docker run -v torontobooks_bigrams.bin:/sent2vec/pretrained_model.bin -it keyphrase-extraction`
that i try two files torontobooks…
-
Hello! I found your answer about how each sentence should look like:
> it is important for machine_learning
But if I want to build my own model, what should I feed to sent2vec?
`../sent2ve…