Opening Computational Door on Knock Knock Jokes

1
Opening Computational Door on Knock Knock Jokes

• Julia M. Taylor Lawrence J. Mazlack
• Applied Artificial Intelligence Laboratory
• University of Cincinnati

2
Introduction

• This is an initial investigation into
  computational humor recognition using wordplay
• The program
• Learns statistical patterns of text
• Recognizes utterances similar in pronunciation to
  a given word
• Determines if found utterances transform a text
  into a joke

3
Restricted Domain Knock Knock Jokes

• Line1 Knock, Knock
• Line2 Whos there?
• Line3 any phrase
• Line4 Line3 followed by who?
• Line5 One or several sentences containing
• Type1 Line3
• Type2 A wordplay on Line3
• Type3 A meaningful response to a wordplay of
  Line3 or Line4

4
Restricted Domain Knock Knock Jokes

• Type1 Line3
• --Knock, Knock
• --Whos there?
• --Water
• --Water who?
• --Water you doing tonight?
• Type2 A wordplay on Line3
• --Knock, Knock
• --Whos there?
• --Ashley
• --Ashley who?
• --Actually, I dont know.
• Type3 A meaningful response to a wordplay of
  Line4
• --Knock, Knock
• --Whos there?
• --Tank
• --Tank who?

5
Experimental Design

• Training set
• 66 Knock Knock jokes
• Enhance similarity table of letters
• Select N-gram training texts
• 66 texts containing wordplay from 66 training
  jokes
• Test set
• 130 Knock Knock jokes
• 66 Non-jokes that have similar structure to
  Knock Knock jokes

6
Similarity Table

• Contains combination of letters that sound
  similar
• Based on similarity table of cross-referenced
  English consonant pairs
• Modified by
• translating phonemes to letters
• adding vowels that are close in sound
• adding other combinations of letters that may be
  used to recognize wordplay

Segment of similarity table
7
Training Corpus

• Training texts were entered into N-gram database
• Nurse I need to get your weight today.
• Impatient patient 3 hours and 45 minutes.
• Wordplay validation bigram table
• (I need 1) (need to 1) (to get 1) (get your 1)
  (your weight 1) (weight today 1) (today
  end-of-sentence 1)
• Punchline validation trigram table
• (I need to 1) (need to get 1) (to get your 1)
  (get your weight 1) (your weight today 1)
  (weight today end-of-sentence 1)

8
How It Works

• Step1 joke format validation
• Step2 computational generation of sound-alike
  sequences
• Step3 validations of a chosen sound-alike
  sequence
• Step4 last sentence validation with sound-alike
  sequence

9
Step 1 Joke Format Validation

• Line1 Knock, Knock
• Line2 Whos there?
• Line3 any phrase
• Line4 Line3 followed by who?
• Line5 One or several sentences containing Line3

• Knock, Knock
• Who is there?
• I, Felix
• I, Felix who?
• I, Felix-ited!

• Knock, Knock
• Who is there?
• I, Felix
• I, Felix who?
• I feel excited!

10
Step 2 Generation of Wordplay Sequences

• Repetitive letter replacements of Line3
• Similarity used for letter replacements
• Resulting utterances are ordered according to
  their similarity with Line3
• Utterances with highest similarity are checked
  for decomposition into several words

Segment of similarity table
11
Step 2 Generation of Wordplay Sequences

ifelixited 10.0
efelixited 9.23
12
Step 2 Generation of Wordplay Sequences

ifelixited 10.0
efelixited 9.23
ifilixited 9.23
ifalixited 9.23
ifolixited 9.23
13
Step 2 Generation of Wordplay Sequences

ifelixited 10.0
efelixited 9.23
ifilixited 9.23
ifalixited 9.23
ifolixited 9.23
iferixited 9.56
14
Step 2 Generation of Wordplay Sequences

ifelixited 10.0
efelixited 9.23
ifilixited 9.23
iferixited 9.56
ifalixited 9.23
ifolixited 9.23
15
Step 2 Generation of Wordplay Sequences

ifelixited 10.0
iferixited 9.56
ifilixited 9.23
efelixited 9.23
ifalixited 9.23
ifolixited 9.23
16
Step 2 Generation of Wordplay Sequences
if el exited
ifelexited 9.23


17
Step 3 Wordplay Validation
if el exited
one word?
NO
YES
divide into pairs
if el el exited
each pair in bigram?
NO
YES
Step 4
Step 2
18
Step 2 Generation of Wordplay Sequences
i feel excited
ifeelexcited 7.x


19
Step 3 Wordplay Validation
i feel excited
one word?
NO
YES
divide into pairs
I feel feel excited
each pair in bigram?
NO
YES
Step 4
Step 2
20
Step 4 Last Sentence Validation with Wordplay

• Wordplay is meaningful
• Could occur
• In the beginning of last sentence
• In the middle of last sentence
• At the end of last sentence

21
Step 4 Last Sentence Validation with Wordplay

• In the beginning of sentence

i feel excited
(wordplay N, punch1, punch2) in trigram?
NO
YES
One word?
YES
NO
(wordplay N-1, wordplay N, punch1) in trigram?
NO
YES
Step 2
joke
Step 2
22
Step 4 Last Sentence Generation with Wordplay

• In the beginning of sentence

i feel excited
Is there sentence in the training text with
wordplay?
NO
YES
Step 2
joke
23
Knock Knock Joke Generation

• --Knock, Knock
• --Whos there?
• --Ammonia
• --Ammonia who?
• --Ammonia

Ammonia Im only
--Knock, Knock --Whos there? --Ammonia --Ammonia
who? --Ammonia trying to be funny
24
Results

• 66 training jokes
• 59 jokes were recognized
• 7 unrecognized, no wordplay found
• 66 non-jokes
• 62 correctly recognized as non-jokes
• 1 found wordplay that makes sense
• 3 incorrectly recognized as jokes
• 130 test jokes
• 8 jokes were not expected to be recognized
• 12 identified as jokes with expected wordplay
• 5 identified as jokes with unexpected wordplay
• 80 expected wordplays found

25
Possible Enhancements

• Improve last sentence validation
• Increasing size of text used for N-gram training
• Parser
• N-grams with stemming
• Improve wordplay generator
• Use of phoneme comparison
• Use wider domain
• All types of Knock Knock jokes
• Other types of wordplay jokes

26
Conclusion

• Initial investigation into KK joke recognition
  using wordplay
• The program was designed to
• Recognize wordplay in KK jokes 67
• Recognize KK jokes containing wordplay 12
• Alternate result of this program
• KK joke generator