Presentation is loading. Please wait.

Presentation is loading. Please wait.

1 I256: Applied Natural Language Processing Marti Hearst Sept 25, 2006.

Similar presentations

Presentation on theme: "1 I256: Applied Natural Language Processing Marti Hearst Sept 25, 2006."— Presentation transcript:

1 1 I256: Applied Natural Language Processing Marti Hearst Sept 25, 2006

2 2 Shallow Parsing Break text up into non-overlapping contiguous subsets of tokens. Also called chunking, partial parsing, light parsing. What is it useful for? Entity recognition – people, locations, organizations Studying linguistic patterns – gave NP – gave up NP in NP – gave NP NP – gave NP to NP Can ignore complex structure when not relevant

3 3 A Relationship between Segmenting and Labeling Tokenization segments the text Tagging labels the text Shallow parsing does both simultaneously.

4 4 Chunking vs. Full Syntactic Parsing “ G.K. Chesterton, author of The Man who was Thursday”

5 5 Representations for Chunks IOB tags Inside, outside, and begin Why do we need a begin tag?

6 6 Representations for Chunks Trees Chunk structure is a two-level tree that spans the entire text, containing both chunks and non-chunks

7 7 CONLL Collection From the Conference on Natural Language Learning Competition from 2000 Goal: create machine learning methods to improve on the chunking task

8 8 CONLL Collection Data in IOB format from WSJ: Word POS-tag IOB-tag Training set: 8936 sentences Test set: 2012 sentences Tags from the Brill tagger Penn Treebank Tags Evaluation measure: F-score 2*precision*recall / (recall+precision) Baseline was: select the chunk tag that is most frequently associated with the POS tag, F =77.07 Best score in the contest was F=94.13

9 9 nltk_lite and CONLL2000 Note that raw hides the IOB format

10 10 nltk_lite and CONLL2000

11 11 nltk_lite and CONLL2000 pp() stands for “pretty print” and applies to the Tree data structure.

12 12 nltk_lite chunks in treebank

13 13 nltk_lite parses in treebank

14 14 Chunking with Regular Expressions This time we write regex’s over TAGS rather than words ? + Compile them with parse.ChunkRule() rule = parse.ChunkRule(‘ +’) chunkparser = parse.RegexpChunk([rule], chunk_node = ‘NP’) Resulting object is of type Tree Top-level node called S Can change this label if you want, in third argument to RegexpChunk

15 15 Chunking with Regular Expressions

16 16 Chunking with Regular Expressions Rule application is sensitive to order

17 17 Chinking Specify what does not go into a chunk. Kind of like specifying punctuation as being not alphanumeric and spaces. Can be more difficult to think about.

18 18 Practice Regexp Chunking Write rules to be able to produce this kind of chunking:

19 19 Next Time Evaluating Shallow Parsing Begin Text Summarization

Download ppt "1 I256: Applied Natural Language Processing Marti Hearst Sept 25, 2006."

Similar presentations

Ads by Google