Sunday, May 29, 2016

Frequency based Spell Checking and Rule based Grammar Checking

To convey the thoughts efficiently, the knowledge of the language and its various rules is very important as thoughts take the form of words and the words take the form of action. One should aim to minimize the errors while using the language. Lesser is the number of mistakes, better will be the communication. To aid in achieving this goal, they are creating a frequency based spell checker and a rule based grammar checker for English language. The grammar checker focuses on detecting and correcting tense related mistakes.

Spell Checking 

One of the error types that can be done while writing spellings is non word error. 
Non word Error: These are the errors where the word doesn‘t exist in the dictionary.
 E.g.
1. He is a gud boy. 
2. She is a nce girl.

 Gud, nce are the words that don‘t exist in English Dictionary.

Correct statements are:  
1. He is a good boy. 
2. She is a nice girl. 

In spell checker the basic tasks are:
1. Error Detection
2. Suggestion Prediction

1. Error Detection Technique 

There are various methods of error detection. They are  mainly using two methods  which are 
  1. Dictionary Lookup Method
  2. N-Gram Technique 
2. Error Correction and Suggestion Prediction Techniques

1. Edit Distance:
        e.g. Distance between the words ‘gud’ and ‘good’ will be 2, since the following two edits can change one into the other, similarly:

G                                 G                            Same
O                                 U                            Substitution of u in place of o
O                                  -                             Deletion of o
D                                 D                            Same

2. Grammar Checking [Rule based approach]
      This is the approach where we match the text with a set of rules and that has been at least POS tagged.
     
2.1 Tense Based Grammar Checker: 
            Tenses are verb-based method used to indicate the time, sometimes the continuation or completeness, of an action. The tenses they are focusing
                      • Present 
                      • Past  
                      • Future




No comments:

Post a Comment