-
Hi,
this is my first time trying this DLA tutorial and finished up till the step of using one of our data driven lexica to make predictions from out text data by running the following command:
dlat…
-
Hey,
I see this has been raised already in #42 , but even on what seems a very simple [example](https://colab.research.google.com/drive/1Qs4UPzX_d07qH5I3QqHiYJj5qoVWJmJZ), I'm getting some odd behavi…
-
Hi Vincent,
I had a question about how `pyfasttext` handles inputs - how do you process sentences, as opposed to individual tokens? For instance, do I need to separately tokenise my input text, or …
-
Otherwise it defaults to "unknown", which is correct on MacOS and Linux (UTF-8) but incorrect on Windows. The following fails on Windows:
```r
tokenize_ngrams("César Moreira Nuñez", n = 1)
```
…
-
posted question [here on stackoverflow](https://stackoverflow.com/questions/51765064/quanteda-how-to-get-ngrams-and-their-frequences-given-n-1-predecessor-words-t
) without answer yet
Is there a wa…
-
Hi, I am using Gensim to load fastText trained model using the code below:
```
from gensim.models.wrappers import FastText
self.word_model = FastText.load_fasttext_format(EMBEDDINGS_MODEL_PATH)
…
-
Are character n-grams present in the pre trained word vectors ?. I tried running the pring-word-vectors function, which prints the word vectors for each of the word from a text file. Fasttext essentia…
-
Unable to write "this is a test" using default 4-key layout.
Single swipe on 4 keys keyboard was unable to get a word prediction for 'is'.
Might also investigate the prediction engine / word fre…
-
Tested version: JATE 2.0 Alpha
Tested schema:
```
…
-
I am using textacy.extract.ngrams to get the n-grams from a doc with both filter_stops and filter_punct
are True. Let's say that the function generates 100 n-grams for us, I am interested to print a…