Natural Language Processing - Introduction to Modern NLP - Part I

1 Natural Language Processing - Introduction to Classical NLP

2 MCQ - Alan Turing published an article titled "Computing Machinery and Intelligence" in the year

3 MCQ - The NLP Layer translates users’ queries (free form) into information that can be used for appropriate responses.

4 MCQ - Which of the following are NLP tools?

5 Natural Language Processing - Creating a Quiz using Text Blob

6 Natural Language Processing - Finding Related Posts using scikit-learn

7 MCQ - Bag of Words Approach ignores order of words, and uses word counts as their basis.

8 MCQ - Vectorization is the step where for each word in the post, its occurrence is counted and noted in a vector.

9 MCQ - Tf-IDF weight is often used in Information retrieval and Text mining

10 MCQ - DialogFlow is an advanced development suite for creating conversational AI applications, including chatbots, voicebots, and IVR bots from Google.

11 Natural Language Processing - Introduction to Modern NLP - Part I

12 Natural Language Processing - Introduction to Modern NLP - Part II

13 Natural Language Processing - Sentiment Analysis

14 MCQ - Char-RNN predicts the next character in a sentence.

15 MCQ - Stateful RNN preserve final state after processing one training batch, and then use it as initial state for next training batch

16 MCQ - The pretrained model components of the TensorFlow Hub project are called

17 Natural Language Processing - Machine Translation

18 MCQ - The TensorFlow Addons project includes many sequence-to-sequence tools to let you easily build production-ready Encoder–Decoders

19 Natural Language Processing - Bi-directional RNN and Beam Search

20 Natural Language Processing - Attention Mechanisms

21 MCQ - Dzmitry Bahdanau et al. introduced a technique that allowed the decoder to focus on the appropriate words (as encoded by the encoder) at each time step in the year

22 MCQ - The Bahdanau attention mechanism is also known as

23 MCQ - Positional embedding generates embeddings using cos and tan functions which allows the model to learn the relative positions of words