Scribd Logo
Upload

Welcome to Scribd!

  • 189 views

    NLP Exam

    Uploaded by

    hazemtarek
    The document contains multiple choice questions about natural language processing and Watson services. It tests knowledge about techniques like normalization, POS tagging, and sentiment analysis. It also contains questions about calculating precision, recall, and the F1 score. Finally, it asks about capabilities of Watson Discovery and how Knowledge Studio can be used to train models.

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd

    NLP Exam

    Uploaded by

    hazemtarek
    189 views3 pages
    The document contains multiple choice questions about natural language processing and Watson services. It tests knowledge about techniques like normalization, POS tagging, and sentiment analysis. It also contains questions about calculating precision, recall, and the F1 score. Finally, it asks about capabilities of Watson Discovery and how Knowledge Studio can be used to train models.

    Original Description:

    NLP exam solution

    Original Title

    NLP exam

    Copyright

    © © All Rights Reserved

    Available Formats

    DOCX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document contains multiple choice questions about natural language processing and Watson services. It tests knowledge about techniques like normalization, POS tagging, and sentiment analysis. It also contains questions about calculating precision, recall, and the F1 score. Finally, it asks about capabilities of Watson Discovery and how Knowledge Studio can be used to train models.

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd
    Download as docx, pdf, or txt
    189 views3 pages

    NLP Exam

    Uploaded by

    hazemtarek
    The document contains multiple choice questions about natural language processing and Watson services. It tests knowledge about techniques like normalization, POS tagging, and sentiment analysis. It also contains questions about calculating precision, recall, and the F1 score. Finally, it asks about capabilities of Watson Discovery and how Knowledge Studio can be used to train models.

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd
    Download as docx, pdf, or txt
    of 3
    At a glance
    Powered by AI
    Some key takeaways from the passages are that normalization is used to unify date formats, POS tagging labels tokens with grammatical information, the F-score formula is 2*(P*R)/(P+R), and Watson Natural Language Classifier cannot be trained with Knowledge Studio.

    The process of labeling tokens with their grammatical label is called POS tagging.

    The formula used to calculate the F-score is 2*(P*R)/(P+R) where P is precision and R is recall.

    The technique that is used to unify all date formats in your data set into one

    common format is called:


     Stemming.
     Tokenization.
     Normalization.
    Normalization

    What is the process of labeling tokens with their grammatical label?


     Tokenization.
     POS tagging.
    C o r r e c t a n s w e r .
     Lexical analysis.
     Parsing.
    For any NLP task, you must apply every step in the NLP pipeline.
     True.
     False.
    C o r r e c t a n s w e r .
    Sentiment analysis is an NLU application.
     True.
    C o r r e c t a n s w e r .
     False.
    To calculate the F-score, you must calculate accuracy first.
     True.
     False.
    C o r r e c t a n s w e r .

    Accuracy is the harmonic mean of precision and recall.


     True.
    W r o n g a n s w e r .
     False.
    Assume that you developed an algorithm and calculated the Precision as 0.5
    and the Recall as 0.5, what is the value of F-score in this case?
     0.25.
     1.00.
     0.50.
    C o r r e c t a n s w e r .
    The F-score is calculated as (hint P=precision, R= Recall):
     2*(P+R)/(P+R).
     2*(P*R)/(P+R).
    C o r r e c t a n s w e r .
     (P*R)/2*(P+R).
     (P+R)/2*(P*R).
    Which of the following inputs can be analyzed by Watson Natural Language
    Understanding?
     Text..
     HTML..
     Public URL..
     All of the above..
    C o r r e c t a n s w e r .
    Watson Discovery News is updated continuously with new articles.
     True.
    C o r r e c t a n s w e r .
     False.
    Watson Discovery provides one of the following capabilities:
     Returns best matching class for a sentence or phrase..
     Identifies a variety of tones at both the sentence and document level..
     Derives insights from transactional and social media data to identify
    psychological traits..
     Adds cognitive search and content analytics to applications to identify patterns,
    trends, and insights..
    C o r r e c t a n s w e r .
    Discovery provides an end-to-end solution that includes document conversion,
    data storage, and a simplified query language.
     True.
    C o r r e c t a n s w e r .
     False.
    Rule-based models are efficient for complex text extraction that has variations.
     True.
     False.
    C o r r e c t a n s w e r .
    ______ defines entities and relationships between entities that are interesting
    for your domain (mentions, entity types, relation types).
     Dictionary.
     Type system.
    C o r r e c t a n s w e r .
     Pre-annotation.
     Ground truth.
    The following Watson service cannot be trained by using Knowledge Studio.
     Watson Natural Language Classifier.
    C o r r e c t a n s w e r .
     Watson Natural Language Understanding.
     Watson Discovery.
    A ruled based model can be used to pre-annotate documents to speed up the
    human annotation process.
     True.
    C o r r e c t a n s w e r .
     False.
    ____ groups words and phrases that should be treated equivalently by a
    model.
     Ruled-based model.
     Ground truth.
     Dictionary.
    C o r r e c t a n s w e r .
     Machine learning model.
     Type system.
    ___ is a collection of vetted data used to adapt a Watson solution to a
    particular domain.
     Ruled-based model.
     Ground truth.
    C o r r e c t a n s w e r .
     Dictionary.
     Machine learning model.
     Type system.
    Finish

    You might also like