How it works...
Chunking (also called shallow parsing) is the analysis of a proposition, which is formed in a simple form by a subject and a predicate. The subject is typically a noun phrase, while the predicate is a verbal phrase formed by a verb with zero or more complements and adverbs. A chunk is made up of one or more adjacent tokens.
There are numerous approaches to the problem of chunking. For example, in the assigned task, a chunk is represented as a group of words delimited by square brackets, for which a tag representing the type of chunk is indicated. The dataset that was used was derived from a given corpora by taking the part related to journal articles and extracting chunks of information from the syntactic trees of the corpora. ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access