cnlp_get_vector

annotation

<p>Word embeddings map each lemma or token into a high-dimensional
vector space. The implementation here uses a 300-dimensional
space. Only available with the spaCy parser.</p>

Provides a set of fast tools for converting a textual corpus into a set of normalized
tables. Users may make use of the 'udpipe' back end with no external dependencies, a Python back
end with 'spaCy' <https://spacy.io> or the Java back end 'CoreNLP'
<http://stanfordnlp.github.io/CoreNLP/>. Exposed annotation tasks include
tokenization, part of speech tagging, named entity recognition, entity linking, sentiment
analysis, dependency parsing, coreference resolution, and word embeddings. Summary
statistics regarding token unigram, part of speech tag, and dependency type frequencies
are also included to assist with analyses.

Taylor Arnold

cleanNLP

cnlp_get_vector: Access word embedding vector from an annotation object

Description

Usage

Arguments

Value

References