Etienne Monneret
Etienne Monneret
The #447 experimentations provide me with an idea. Like me, you certainly often see that NMT are loosing some words in the translations. Here is an example of the involved...
Suppose I want to translate this EN sentence: > The Madagascans voted in a peaceful atmosphere in a transparent and well-organised poll, mission head Cristian Preda told reporters. The model...
I have to build a FR-JP model, and I don't find large parallel resources. First of all, do you know about a large FR-JP corpus somewhere ? I just have...
Hi all! Yesterday, I just did a test to include svgSalamander to read SVG input files in my 3D-stereo freeware: http://3denlive.com/en.php When using this `Gnome_All.svg` file with a dark-pink text...
As requested in #41, here is how I succeeded in running contextualSpellCheck for French. Use French spaCy model: ``` nlp = spacy.load("fr_core_news_sm") ``` Use `camembert/camembert-base-ccnet`: ``` nlp.add_pipe("contextual spellchecker", config={"max_edit_dist": 4,"model_name":...
Hi all, In the documentation, I read: `--lr-decay-inv-sqrt: learning rate will be decreased at n / sqrt(no. updates) starting at n-th update` Trying to understand what kind of value I...
I do not find such an option in the documentation. :)
Hi! What I'm doing is a bit particular: translating noisy text to denoised clean text (for NeuroSpell auto-corrector). On the principle, it should not cause the strange thing described below....