From 388212165fe64c3ad03ed2e51aaee9328f7c0a05 Mon Sep 17 00:00:00 2001 From: nprimo Date: Mon, 11 Dec 2023 13:11:38 +0000 Subject: [PATCH] feat(nlp-spacy/ex5): update specifications and audit question --- subjects/ai/nlp-spacy/README.md | 2 +- subjects/ai/nlp-spacy/audit/README.md | 8 ++------ 2 files changed, 3 insertions(+), 7 deletions(-) diff --git a/subjects/ai/nlp-spacy/README.md b/subjects/ai/nlp-spacy/README.md index 76ee893f3..8af36ce59 100644 --- a/subjects/ai/nlp-spacy/README.md +++ b/subjects/ai/nlp-spacy/README.md @@ -84,7 +84,7 @@ The goal of this exercise is to learn to tokenize a document using `spaCy`. We d The goal of this exercise is to learn to use `spaCy` embedding on a document. -1. Compute the embedding of all the words in this sentence. The language model considered is `en_core_web_md` +1. Compute the embedding of all the words in this sentence. The language model considered is `en_core_web_md` version 3.4.1. ``` "laptop computer coffee tea water liquid dog cat kitty" diff --git a/subjects/ai/nlp-spacy/audit/README.md b/subjects/ai/nlp-spacy/audit/README.md index 1a5edaf27..2ce3b3196 100644 --- a/subjects/ai/nlp-spacy/audit/README.md +++ b/subjects/ai/nlp-spacy/audit/README.md @@ -48,14 +48,10 @@ ##### The exercise is validated if all questions of the exercise are validated -###### For question 1, have the embeddings of each word a shape of `(300,)` and are the first 20 values of the embedding of laptop the following? +###### For question 1, have the embeddings of each word a shape of `(300,)` and is the sum of the first 20 values of the embedding of laptop the following? ``` -array([-0.37639 , -0.075521, 0.4908 , 0.19863 , -0.11088 , -0.076145, - -0.30367 , -0.69663 , 0.87048 , 0.54388 , 0.42523 , 0.18045 , - -0.4358 , -0.32606 , -0.70702 , -0.069127, -0.42674 , 2.4147 , - 0.26806 , 0.46584 ], dtype=float32) - +5.710388 ``` ###### For question 2, is the output the following?