Quizz 01: General Intro to NLP

1. Distinguish between the Natural Language Processing and Computational Linguistics approaches to the field of computer-aided study of human languages.

   
   
   
   
   

2. List five properties of natural language which make computational processing of natural language difficult.

   
   
   
   
   
   
   

3. Define what is a "sign" according to the technical semiotic definition.

   
   
   
   
   
   
   

4. Consider the various definitions of the linguistic unit called "word": orthographic (sequence of letters separated by delimiters); semantic (an independent unit of meaning); dictionary (a unit which is listed in the lexicon of the language). For each of the following cases, indicate whether the classification of the string between brackets as a single word according to the [O]rthographic, [S]emantic [D]ictionary sense:

   
   It [isn't] too late
   
   [Bob's] hat is yellow
   
   [Come on]
   
   Let's have a [follow-up] call tomorrow
   
   [New York City] counts five boroughs
   
   [Two hundred and fifty five] students attended the event
   

5. How many distinct words are there in Hebrew? Describe a computational procedure to estimate this number. List parameters which can make the question more precise.

   
   
   
   
   
   
   

6. The "Open Information Extraction" tool at AllenAI returns incorrect answers for this query: who governs the United States. For each of the following sentence that was matched by this query, explain what is the source of the mistake: Lexical knowledge, Syntax, Semantics.

   
   Answer: AFRICA / We Africans are happy, proud that a son of Africa governs the United States of America
   
   Answer: LAW / The House of Representatives drafts and passes laws that, when signed by the president, govern the Unites States and its citizens.
   
   Answer: THE SITE / All matters relating to the site are governed by United States Law.