-
@amayadwillis I noticed this on your new task list, and was thinking about it. Are these ngrams that you pulled from analysis with Antconc?
If we can make a plain text list of these, we can use `` …
-
@dimaztest, does the library allow downloads for versions other than `20120701` ?
-
Calculate the uni-, bi-, and trigram log-probabilities of the data in “Brown_train.txt”. This
corresponds to implementing the calc_probabilities() function. In this assignment we will always
use log b…
-
**Describe the bug**
The `str.character_ngrams` function produces token `` for strings which are lesser than the provided `n` (shown in image for the case of bigrams).
![result output](https://githu…
-
Hi Jack,
Thanks for the great work and sharing the code! I am trying to reproduce results from the paper and want to confirm if I am doing it correctly.
Specifically I ran the below code
```
…
-
Hi Andrew, again me :)
I want to ask two questions about the algorithm.
When using the first BERT model, why are we remove ngrams and can't we use them without remove ngrams?
My second question is …
-
![screenshot from 2019-03-04 20-54-02](https://user-images.githubusercontent.com/218561/53828361-6c162b00-3f4b-11e9-9c02-06028501c65a.png)
As pitched in the #auk channel on Archives Unleashed Slack
-
https://storage.googleapis.com/books/ngrams/books/datasetsv3.html . For an URL example, one file of ngrams is at http://storage.googleapis.com/books/ngrams/books/20200217/eng/1-00016-of-00024.gz
-
Hi, I have some confusion about the lines (127-133) in feature_extractor.py , I can't understand why 'good_grammar_ratio' should calculated like that. As I see it, good_grammar_ratio should be calcu…
-
NEWSPAPERS
- [ ] Newspapers page: Unclear: which parts are missing within the span of a newspaper
- [ ] No legend: how was this calculated, what are we missing? For @mduering to add to FAQ entries…