SIMS 290-2: Applied Natural Language Processing

1. SIMS 290-2: Applied Natural Language Processing Marti Hearst Sept 20, 2004

2. Today • Handout: basic English grammar • Determine time for a one-time lab • Begin chunking/shallow parsing

3. 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 Slide modified from Steven Bird's

4. 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]? Slide modified from Steven Bird's

5. Shallow Parsing: 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 Slide modified from Steven Bird's

6. Representation • BIO (or IOB)Trees Slide modified from Steven Bird's

7. Comparison with Full Syntactic 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 Slide modified from Steven Bird's

8. 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 Slide modified from Steven Bird's

9. 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) Slide modified from Steven Bird's

10. Chunking • Define a regular expression that matches the sequences of tags in a chunk A simple noun phrase chunk regexp: (Note that <NN.*> matches any tag starting with NN) <DT>? <JJ>* <NN.?> • Chunk all matching subsequences: the/DT little/JJ cat/NN sat/VBD on/IN the/DT mat/NN [the/DTlittle/JJcat/NN] sat/VBD on/IN[the/DTmat/NN] • If matching subsequences overlap, first 1 gets priority Slide modified from Steven Bird's

11. Unchunking • Remove any chunk with a given pattern • e.g., unChunkRule(‘<NN|DT>+’, ‘Unchunk NNDT’) • Combine with Chunk Rule <NN|DT|JJ>+ • Chunk all matching subsequences: • Input: the/DT little/JJ cat/NN sat/VBD on/IN the/DT mat/NN • Apply chunk rule [the/DTlittle/JJcat/NN] sat/VBD on/IN[the/DTmat/NN] • Apply unchunk rule [the/DTlittle/JJcat/NN] sat/VBD on/INthe/DTmat/NN

12. 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: (<VB.?>|<IN>)+ • 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/DTlittle/JJcat/NN]sat/VBD on/IN[the/DTmat/NN] Chunk Chink Chunk Slide modified from Steven Bird's

13. 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(‘<JJ>’, ‘<NN>’, ‘Merge adjs and nouns’) [the/DTlittle/JJ][cat/NN] sat/VBD on/IN the/DT mat/NN [the/DTlittle/JJcat/NN] sat/VBD on/IN the/DT mat/NN • Splitting is the opposite of merging Slide modified from Steven Bird's

14. Tokens and Labels in NLTK • Tokens are at many levels of description • Document • Sentence • Word • Can have multiple representations at the same level • A sentence can be marked up with TREE and WORDS simultaneously • A word can have both TEXT and POS (or TAG)

15. Applying Chunking to Treebank Data

18. Usually resolve this kind of problem by checking out the API: http://nltk.sourceforge.net/api-1.4/index.html But not all that helpful in this case. Tutorial has the answer.

20. Cascaded Chunking Slide modified from Steven Bird's

21. Next Time and Upcoming • Finish Shallow Parsing • Evaluating Shallow Parsing Results • More examples of chunk/chink/unchunk rules • Revisit topics from previous week • Shallow Parsing Assignment • Sent out Tues or Wed • Due on Wed Sept 29 • Next week: • Read paper on end-of-sentence disambiguation • Presley and Barbara lecturing on categorization