Topic 1 Question 176
2 つ選択A machine learning (ML) specialist needs to extract embedding vectors from a text series. The goal is to provide a ready-to-ingest feature space for a data scientist to develop downstream ML predictive models. The text consists of curated sentences in English. Many sentences use similar words but in different contexts. There are questions and answers among the sentences, and the embedding space must differentiate between them. Which options can produce the required embedding vectors that capture word context and sequential QA information?
Amazon SageMaker seq2seq algorithm
Amazon SageMaker BlazingText algorithm in Skip-gram mode
Amazon SageMaker Object2Vec algorithm
Amazon SageMaker BlazingText algorithm in continuous bag-of-words (CBOW) mode
Combination of the Amazon SageMaker BlazingText algorithm in Batch Skip-gram mode with a custom recurrent neural network (RNN)
解説
ユーザの投票
コメント(13)
- 正解だと思う選択肢: AC
seq2seq and object2vec take care of more than just the words. Any response with blazingText is wrong because blazingText just uses a cbow (continuous bag of words), working only on individual words
👍 14ovokpus2022/06/26 - 正解だと思う選択肢: BD
It should be B an D. The objective is to create a latent space/word embedding that puts similar words closer to each other for other purposes. Thus, we should use Sagemaker Blazing Text in unsupervised mode (Word2Vec mode). cbow, skip-grams, and batch skip-grams are the 3 algorithms for this. However, since we do not need to do the later part of E, E is not correct. The ans should be B and D.
👍 7peterfish2022/07/19 I believe it should be C and E
👍 4phani19892022/06/30
シャッフルモード