Page 291 - AI Ver 1.0 Class 10
P. 291

• Same syntax with different meaning:

                   print(4/2) #is 2 in Python 2.7 i.e. The result is integer

                   print(4/2) #is 2.0 in Python 3.0 onwards i.e. The result is float
                    • Correct syntax but no meaning:

                   print() #with nothing inside to be given as output on screen


                 Multiple Meanings of the words in English Language

                 English is mostly used as a natural language. It is a language where a word can have multiple meanings and the
                 meanings fit into the statement according to the context of it.
                 For example:

                    • His future is very bright.
                    • Today the Sun is very bright

                 In the above sentences the word bright is playing a different role. This kind of situation can be easily handled by
                 humans using their intellectual power and through their language skills.

                 Teaching a computer to understand and interact in human language is a very challenging job. Now let us study
                 how Natural Language Processing makes it possible for the machines to understand and speak in the Natural
                 Languages just like humans.


                         Data Processing



                 Making a computer understand a natural language is a complex process. First, we need to understand that humans
                 interact using alphabets and sentences and machines interact using numbers. So, to make the machine learn and
                 process a sentence in terms of numbers we first need to follow a Pre-Processing Stage of NLP about which we will
                 study in detail.


                 Text Normalisation

                 This is the process of cleaning the textual data by converting a text into a standard form. It is considered as the
                 Pre-Processing stage of NLP as this is the first thing to do before we begin the actual data processing. It helps
                 in reducing the complexity of the language. Words used as slang, short forms, misspelled, abbreviations, special
                 meaning characters etc. need to be converted into a canonical form after Text Normalisation. For example:


                                                    Words                   Canonical form

                                          B4, beefor, bifore           before


                                          2morrow, 2mrow               tomorrow


                                          btw                          by the way


                                          ty                           thank you



                                                                               Natural Language Processing  289
   286   287   288   289   290   291   292   293   294   295   296