Shallow Parsing, Full Sentence Parsing - Study Guide | CSE 591, Exams of Computer Science

Download Shallow Parsing, Full Sentence Parsing - Study Guide | CSE 591 and more Exams Computer Science in PDF only on Docsity!

CSE 591

Natural language processing

-Shallow parsing, full sentence parsing-

Fall 2008 http://www.public.asu.edu/~jhakenbe/591/

Class format

• two exams: mid-term and final
  • test theoretical aspects and principles
• class project: three^ building blocks
  • named entity recognition
    • protein, drug, disease, organ/tissue, biol. process, cell. location
  • sentence classification
    • discusses certain type of relation?
  • relation mining
    • find partners in relation

Period disambiguation

• many (sub)tasks work on^ sentence level^ instead of whole text
  • POS-tagging, parsing
  • relation mining, machine translation, summarization
• splitting a text into sentence^ not a trivial task
• good heuristic: split at “lower-case---period---white space---upper case” sequence ... found to be 9.8 (p < 0.0005) ... => 2x no ... on the X chromosome. The ... => yes ... as published by A. Greenfield et al. in ... => 2x no ... by A. Greenfield et al. This study ... => no, yes ... found (A. Greenfield. ICMLʼ07, 14-28) ... => 2x no ... found as fibronectin A. Greenfield showed that ... => yes

Period disambiguation

• fixed rule-based vs machine learning
  • ML: supervised vs unsupervised
• rule-based: some heuristics + special cases
  • l.c. + period + white space + u.c.
  • no split within parenthesis
  • no split after^ known^ abbreviations (vs., etc., pp., …)
  • no split if a sentence <3 words results

Chunking

• identify^ constituents^ in a sentence
  • word or group that functions as a^ single unit^ in a sentence
• split a sentence into chunks:
  • noun groups, verb groups
  • compound nouns etc.
• also called^ shallow parsing,^ light parsing
• but: not internal structure, not role in sentence ➱ that would be full sentence parsing

Chunking

• usually solved using regular expressions
  • tag patterns
• simple examples:
• more complex examples:
  + <NN|JJ>
  ?<JJ.><NN.>+ another/DT sharp/JJ dive/NN trade/NN figures/NNS any/DT new/JJ policy/NN measures/NNS earlier/JJR stages/NNS Panamanian/JJ dictator/NN Manuel/NNP Noriega/NNP his/PRP$ Mansion/NNP House/NNP speech/NN the/DT price/NN cutting/VBG 3/CD %/NN to/TO 4/CD %/NN more/JJR than/IN 10/CD %/NN the/DT fastest/JJS developing/VBG trends/NNS 's/POS skill/NN

Sentence parsing

• so far: category of^ each word^ (POS), constituents
• now: dependencies/links^ between words
  • subject-object
  • subject-verb-object
  • determiner-adjective-noun
• parsing: discover^ sentence structure POS tokens chunks parse

Sentence parsing

• Example: context free grammar covers linguistic knowledge
• terminal (“home”) and non-terminal (“VP”) parts
• CFG:^ “problem reduction”
• top-down / bottom-up parse
• left-right / right/left parse

Examples for links

• S: connects subject nouns to verbs
  • Ss: singular noun & verb, Sp: plural
• D: determiner to noun
• O: direct/indirect objects to transitive verbs
• see^ http://www.link.cs.cmu.edu/link/dict/index.html +---------------------Xp---------------------+ +------Wd-----+ +------ Os -----+ | | +--Ds--+---- Ss ---+ +---Ds--+ | | | | | | | | LEFT-WALL the burglar.n robbed.v the apartment.n.

POS-tagging in LG

• LinkGrammar parser handles POS tagging
  • many other parsers require tagged sentence as input
• POS-tagging in 3 stages:
  1. dictionary-lookup, or for unknown words:
  2. guess based on morphology (suffix)
  3. assign noun/verb/adjective & validate link requirement +------------------Xp-----------------+ | +------Ost------+ | | | +-----Ds-----+ | +----Wd---+--Ss--+ | +---A---+ | | | | | | | | LEFT-WALL xyz [?].n is.v a great.a movie.n. Possible links for “noun”

Summary

• text (➠^ paragraphs)^ ➠^ sentences^ ➠^ word forms^ ➠^ tokens^ ➠^ part-of-speech ➠ constituents ➠ sentence structure
• all: features for subsequent tasks ➱ text classification / information retrieval (IR) / word sense disambiguation (WSD)
• word form / POS / sequence of words: ➱ information extraction (IE) / named entity recognition (NER)
• POS / constituents / sentence structure: ➱ relation mining (RM)
• note that there might also be^ circular dependencies:
  • “I saw her^ duck^ under the table”
  • WSD to get the correct grammatical structure
  • guessing the structure might help WSD

Bibliography

• Period disambiguation
  • Grefenstette & Tapanainen:^ What is a word, what is a sentence? Problems of tokenization. 1994.
  • H. Schmid:^ Unsupervised learning of period disambiguation for tokenisation.^ Tech Report, 2000.
  • Mikheev:^ Document centered approach to text normalization.^ ACM SIGIR , 2000.
• Sentence parsing
  • Wikipedia
• Link Grammar
  • Temperley & Sleator: see^ http://www.link.cs.cmu.edu/link/
  • Pyysalo: BioLG - Lexical adaption of Link Grammar to the biomedical sublanguage. 2006.
• Biomedical NLP / text mining
  • Bruijn & Martin: Getting to the (C)ore of knowledge: mining biomedical literature. 2002.
  • Cohen & Hersh:^ A survey of current work in biomedical text mining. 2005.
  • Cohen & Hunter: Getting started in text mining.^ PLoS Comp Biol , 2008.
• Books on various topics Search for last name, year & title to get PDFs. CiteseerX.