1. 1 I256: Applied Natural Language Processing Marti Hearst Sept 13, 2006

2. 2 Counting Tokens Useful for lots of things One cute application: see who talks where in a novel Idea comes from Eick et al. who did it with The Jungle Book by Kipling

3. 3 SeeSoft Vizualization of Jungle Book Characters, From Eick, Steffen, and Sumner ‘92

4. 4 The FreqDist Data Structure Purpose: collect counts and frequencies for some phenomenon Initialize a new FreqDist: from nltk_lite.probability import FreqDist fd = FreqDist() When in a counting loop: fd.inc(‘item of interest’) After done counting: fd.N() # total number of tokens counted fd.B() # number of unique tokens fd.samples() # list of all the tokens seen (there are N) fd.Nr(10) # number of samples that occurred 10 times fd.count(‘red’) # number of times the token ‘red’ was seen fd.freq(‘red’) # frequency of ‘red’; that is fd.count(‘red’)/fd.N() fd.max() # which token had the highest count fd.sorted_samples() # show the samples in decreasing order of frequency

5. 5 FreqDist() in action

6. 6 Word Lengths by Language

7. 7

8. 8 Doing Character Distribution

9. 9 How to determine the characters? Write some code that takes as input a gutenberg file and quickly suggests who the main characters are.

10. 10 How to determine the characters? My solution: look for words that begin with capital letters; count how often each occurs. Then show the most frequent.

11. 11

12. 12 Language Modeling A fundamental concept in NLP Main idea: For a given language, some words are more likely than others to follow each other, or You can predict (with some degree of accuracy) the probability that a given word will follow another word.

13. 13 Adapted from slide by Bonnie Dorr Next Word Prediction From a NY Times story... Stocks... Stocks plunged this …. Stocks plunged this morning, despite a cut in interest rates Stocks plunged this morning, despite a cut in interest rates by the Federal Reserve, as Wall... Stocks plunged this morning, despite a cut in interest rates by the Federal Reserve, as Wall Street began

14. 14 Adapted from slide by Bonnie Dorr Human Word Prediction Clearly, at least some of us have the ability to predict future words in an utterance. How? Domain knowledge Syntactic knowledge Lexical knowledge

15. 15 Adapted from slide by Bonnie Dorr Simple Statistics Does a Lot A useful part of the knowledge needed to allow word prediction can be captured using simple statistical techniques In particular, we'll rely on the notion of the probability of a sequence (a phrase, a sentence)

16. 16 Adapted from slide by Bonnie Dorr N-Gram Models of Language Use the previous N-1 words in a sequence to predict the next word How do we train these models? Very large corpora

17. 17 Adapted from slide by Bonnie Dorr Simple N-Grams Assume a language has V word types in its lexicon, how likely is word x to follow word y? Simplest model of word probability: 1/V Alternative 1: estimate likelihood of x occurring in new text based on its general frequency of occurrence estimated from a corpus (unigram probability) popcorn is more likely to occur than unicorn Alternative 2: condition the likelihood of x occurring in the context of previous words (bigrams, trigrams,…) mythical unicorn is more likely than mythical popcorn

18. 18 ConditonalFreqDist() Data Structure A collection of FreqDist() objects Indexed by the “condition” that is being tested or compared Initialize a new one: cfd = ConditionalFreqDist() Add a count cfd[‘berkeley’].inc(‘blue’) cfd[‘berkeley’].inc(‘gold’) cfd[‘stanford’].inc(‘red’) Can access each FreqDist object by indexing on condition cfd[‘berkeley’].samples() cfd[‘berkeley’].N() Can also get a list of the conditions from the cfd object cfd.conditions() >> [‘stanford’, ‘berkeley’]

19. 19 Computing Next Words

20. 20 Auto-generate a Story

21. 21 Adapted from slide by Bonnie Dorr Applications Why do we want to predict a word, given some preceding words? Rank the likelihood of sequences containing various alternative hypotheses, e.g. for ASR Theatre owners say popcorn/unicorn sales have doubled... Assess the likelihood/goodness of a sentence –for text generation or machine translation. The doctor recommended a cat scan. El doctor recommendó una exploración del gato.

22. 22 How to implement this? Comparing Modal Verb Counts

23. 23 Comparing Modals

24. 24 Comparing Modals

25. 25 Next Time Part of Speech Tagging