Glossary term
Glossary term
Foundations
Dividing a sentence into smaller grammatical structures ("constituents"). A later part of the ML system, such as a natural language understanding model, can parse the constituents more easily than the original sentence. For example, consider the following sentence:
My friend adopted two cats.
A constituency parser can divide this sentence into the following two constituents:
My friend is a noun phrase.
adopted two cats is a verb phrase.
These constituents can be further subdivided into smaller constituents. For example, the verb phrase
adopted two cats
could be further subdivided into:
adopted is a verb.
two cats is another noun phrase.
Created for this library
A legal-tech vendor uses constituency parsing on contract sentences to extract noun phrases that describe obligations and parties.
A search-quality team uses constituency parsing on long user queries to identify the head noun phrase and rank documents accordingly.
A customer support analytics team uses constituency parsing on ticket text to extract product mentions and route tickets to the right team.
Definition source: Google for Developers Machine Learning Glossary | Creative Commons Attribution 4.0 License