1. October 2005CSA3180: Text Processing II1 CSA3180: Natural Language Processing Text Processing 2 Shallow Parsing and Chunking Python and NLTK NLTK Exercises

2. October 2006csa3180: Parsing Algorithms 12 Parsing Problem Given grammar G and sentence A discover all valid parse trees for G that exactly cover A S VP NP V Det Nom N book that flight

3. October 2006csa3180: Parsing Algorithms 13 The elephant is in the garden I shot an elephant in my garden NP VP NP PP NP S

4. October 2006csa3180: Parsing Algorithms 14 I own the garden I shot an elephant in my garden NP VP PP NP S

5. October 2006csa3180: Parsing Algorithms 15 Parsing as Search Search within a space defined by –Start State –Goal State –State to state transformations Two distinct parsing strategies: –Top down –Bottom up Different parsing strategy, different state space, different problem. N.B. Parsing strategy ≠ search strategy

6. October 2005CSA3180: Text Processing II6 Shallow/Chunk Parsing Goal: divide a sentence into a sequence of chunks. Chunks are non-overlapping regions of a text [I] saw [a tall man] in [the park]. Chunks are non-recursive – A chunk can not contain other chunks Chunks are non-exhaustive – Not all words are included in chunks

7. October 2005CSA3180: Text Processing II7 Chunk Parsing Examples Noun-phrase chunking: [I] saw [a tall man] in [the park]. Verb-phrase chunking: The man who [was in the park] [saw me]. Prosodic chunking: [I saw] [a tall man] [in the park]. Question answering: –What [Spanish explorer] discovered [the Mississippi River]?

8. October 2005CSA3180: Text Processing II8 Motivation Locating information –e.g., text retrieval Index a document collection on its noun phrases Ignoring information –Generalize in order to study higher-level patterns e.g. phrases involving “gave” in Penn treebank: –gave NP; gave up NP in NP; gave NP up; gave NP help; gave NP to NP –Sometimes a full parse has too much structure Too nested Chunks usually are not recursive

9. October 2005CSA3180: Text Processing II9 Representation BIO (or IOB) Trees

10. October 2005CSA3180: Text Processing II10 Comparison with Full Parsing Parsing is usually an intermediate stage –Builds structures that are used by later stages of processing Full parsing is a sufficient but not necessary intermediate stage for many NLP tasks –Parsing often provides more information than we need Shallow parsing is an easier problem –Less word-order flexibility within chunks than between chunks –More locality: Fewer long-range dependencies Less context-dependence Less ambiguity

11. October 2005CSA3180: Text Processing II11 Chunks and Constituency Constituents: [[a tall man] [ in [the park]]]. Chunks: [a tall man] in [the park]. A constituent is part of some higher unit in the hierarchical syntactic parse Chunks are not constituents – Constituents are recursive But, chunks are typically subsequences of constituents – Chunks do not cross major constituent boundaries

12. October 2005CSA3180: Text Processing II12 Unchunking Remove any chunk with a given pattern –e.g., unChunkRule(‘ +’, ‘Unchunk NNDT’) –Combine with Chunk Rule + Chunk all matching subsequences: –Input: the/DT little/JJ cat/NN sat/VBD on/IN the/DT mat/NN –Apply chunk rule [ the/DT little/JJ cat/NN ] sat/VBD on/IN [ the/DT mat/NN ] –Apply unchunk rule [ the/DT little/JJ cat/NN ] sat/VBD on/IN the/DT mat/NN

13. October 2005CSA3180: Text Processing II13 Chinking A chink is a subsequence of the text that is not a chunk. Define a regular expression that matches the sequences of tags in a chink A simple chink regexp for finding NP chunks: ( | )+ First apply chunk rule to chunk everything –Input: the/DT little/JJ cat/NN sat/VBD on/IN the/DT mat/NN –ChunkRule(' +', ‘Chunk everything’) [ the/DT little/JJ cat/NN sat/VBD on/IN the/DT mat/NN ] –Apply Chink rule above: [ the/DT little/JJ cat/NN ] sat/VBD on/IN [ the/DT mat/NN ]

14. October 2005CSA3180: Text Processing II14 Merging Combine adjacent chunks into a single chunk –Define a regular expression that matches the sequences of tags on both sides of the point to be merged Example: –Merge a chunk ending in JJ with a chunk starting with NN MergeRule(‘ ’, ‘ ’, ‘Merge adjs and nouns’) [ the/DT little/JJ ] [ cat/NN ] sat/VBD on/IN the/DT mat/NN [ the/DT little/JJ cat/NN ] sat/VBD on/IN the/DT mat/NN Splitting is the opposite of merging

15. October 2005CSA3180: Text Processing II15 Python and NLTK Natural Language Toolkit (NLTK) http://nltk.sourceforge.net/ NLTK Slides partly based on Diane Litman Lectures Chunk parsing slides partly based on Marti Hearst Lectures

16. October 2005CSA3180: Text Processing II16 Python for NLP Python is a great language for NLP: –Simple –Easy to debug: Exceptions Interpreted language –Easy to structure Modules Object oriented programming –Powerful string manipulation

17. October 2005CSA3180: Text Processing II17 Python Modules and Packages Python modules “package program code and data for reuse.” (Lutz) –Similar to library in C, package in Java. Python packages are hierarchical modules (i.e., modules that contain other modules). Three commands for accessing modules: 1.import 2.from…import 3.reload

18. October 2005CSA3180: Text Processing II18 Import Command The import command loads a module: # Load the regular expression module >>> import re To access the contents of a module, use dotted names: # Use the search method from the re module >>> re.search(‘\w+’, str) To list the contents of a module, use dir: >>> dir(re) [‘DOTALL’, ‘I’, ‘IGNORECASE’,…]

19. October 2005CSA3180: Text Processing II19 from...import The from…import command loads individual functions and objects from a module: # Load the search function from the re module >>> from re import search Once an individual function or object is loaded with from…import, it can be used directly: # Use the search method from the re module >>> search (‘\w+’, str)

20. October 2005CSA3180: Text Processing II20 Import vs. from...import Import Keeps module functions separate from user functions. Requires the use of dotted names. Works with reload. from…import Puts module functions and user functions together. More convenient names. Does not work with reload.

21. October 2005CSA3180: Text Processing II21 Reload If you edit a module, you must use the reload command before the changes become visible in Python: >>> import mymodule... >>> reload (mymodule) The reload command only affects modules that have been loaded with import ; it does not update individual functions and objects loaded with from...import.

22. October 2005CSA3180: Text Processing II22 NLTK Introduction The Natural Language Toolkit (NLTK) provides: –Basic classes for representing data relevant to natural language processing. –Standard interfaces for performing tasks, such as tokenization, tagging, and parsing. –Standard implementations of each task, which can be combined to solve complex problems.

23. October 2005CSA3180: Text Processing II23 NLTK Example Modules nltk.token : processing individual elements of text, such as words or sentences. nltk.probability : modeling frequency distributions and probabilistic systems. nltk.tagger : tagging tokens with supplemental information, such as parts of speech or wordnet sense tags. nltk.parser : high-level interface for parsing texts. nltk.chartparser : a chart-based implementation of the parser interface. nltk.chunkparser : a regular-expression based surface parser.

24. October 2005CSA3180: Text Processing II24 Chunk Parsing in NLTK Chunk parsers usually ignore lexical content –Only need to look at part-of-speech tags Possible steps in chunk parsing –Chunking, unchunking –Chinking –Merging, splitting Evaluation –Compare to a Baseline –Evaluate in terms of Precision, Recall, F-Measure Missed (False Negative), Incorrect (False Positive)

25. October 2005CSA3180: Text Processing II25 Chunk Parsing in NLTK Define a regular expression that matches the sequences of tags in a chunk A simple noun phrase chunk regexp: (Note that matches any tag starting with NN) ? * Chunk all matching subsequences: the/DT little/JJ cat/NN sat/VBD on/IN the/DT mat/NN [ the/DT little/JJ cat/NN ] sat/VBD on/IN [ the/DT mat/NN ] If matching subsequences overlap, first 1 gets priority

26. October 2005CSA3180: Text Processing II26 NLTK Exercises for Next Week Series of tutorials by Steven Bird, Edward Klein and Edward Loper –http://nltk.sourceforge.net/http://nltk.sourceforge.net/ –University of Pennsylvania By next lecture please read and do exercises in: –Introduction –Programming –Tokenize –Tag

27. October 2005CSA3180: Text Processing II27 Next Sessions… Natural Language Toolkit (NLTK) Exercises http://nltk.sourceforge.net/ Discovery of Word Associations Text Classification Clustering/Data Mining TF.IDF Linear and Non-Linear Classification Binary Classification Multi-Class Classification