TaPvex

Tagged and Phrased Word Vectors



Abstract:

TaPvex is a trained word2vec model of part-of-speech-tagged and named-entity-tagged words and phrases. The model was trained on a large corpus of English language news text from the early 2010s. Words have been tagged using Stanford CoreNLP to include named entities (NER) and Penn Treebank parts-of-speech (POS). Tagged words have been concatenated into n-gram phrases.

The model contains 1.17 million unique words and phrases. Word vectors are of size 150.

Use

All three files (TaPvex, TaPvex.syn0.npy, TaPvex.syn1.npy) must be located in the same directory. The file can be opened with the gensim Python module using:

from gensim.models import Word2Vec
model = Word2Vec.load("/path/to/model/TaPvex")

Examples

Tokens are of the form:

[WORD]:[NER]:[POS]

Phrases are of the form:

[WORD]:[NER]:[POS]_[WORD]:[NER]:[POS]

Example tokens include:

BUSH:O:NN
BUSHES:O:NNS
BUSH:PERSON:NNP
GEORGE:PERSON:NNP_BUSH:PERSON:NNP 
GEORGE:PERSON:NNP_W:PERSON:NNP_BUSH:PERSON:NNP

NEW:O:JJ
NEW:LOCATION:NNP_YORK:LOCATION:NNP
NEW:ORGANIZATION:NNP_YORK:ORGANIZATION:NNP_TIMES:ORGANIZATION:NNP