Shallow parsing

Shallow parsing(alsochunkingorlightparsing) is an analysis of asentencewhich first identifies constituent parts of sentences (nouns, verbs, adjectives, etc.) and then links them to higher order units that have discrete grammatical meanings (noungroups orphrases,verb groups, etc.). While the most elementary chunking algorithms simply link constituent parts on the basis of elementary search patterns (e.g., as specified byregular expressions), approaches that usemachine learning techniques(classifiers,topic modeling,etc.) can take contextual information into account and thus compose chunks in such a way that they better reflect the semantic relations between the basic constituents.That is, these more advanced methods get around the problem that combinations of elementary constituents can have different higher level meanings depending on the context of the sentence.

It is a technique widely used innatural language processing.It is similar to the concept oflexical analysisfor computer languages. Under the name "shallow structure hypothesis", it is also used as an explanation for whysecond languagelearners often fail to parse complex sentences correctly.

References

Sources

• "NP Chunking (State of the art)".Association for Computational Linguistics.Retrieved2016-01-30.
• Abney, Steven (1991)."Parsing By Chunks | Principle-Based Parsing"(PDF).www.vinartus.net.pp. 257–278.

External links

• Apache OpenNLPOpenNLPincludes a chunker.
• GATE General Architecture for Text EngineeringGATEincludes a chunker.
• NLTKchunking
• Illinois Shallow ParserShallow ParserDemo

See also

• Parser
• Semantic role labeling
• Named entity recognition