Commit
•
7d259e7
1
Parent(s):
1a7b275
upload vocab
Browse files
README.md
CHANGED
@@ -22,7 +22,7 @@ widget:
|
|
22 |
|
23 |
# EarningsCall2Vec
|
24 |
|
25 |
-
**EarningsCall2Vec** is a [fastText](https://fasttext.cc/) word embedding model that was trained via [Gensim](https://radimrehurek.com/gensim/). It maps each token in the vocabulary to a dense, 300-dimensional vector space, designed for performing **semantic search**. More details about the training procedure can be found
|
26 |
|
27 |
|
28 |
## Background
|
@@ -69,13 +69,10 @@ model = load_facebook_model(<PATH-MODEL>)
|
|
69 |
|
70 |
# extract word embeddings
|
71 |
model.wv['transformation']
|
72 |
-
|
73 |
# get similar phrases
|
74 |
model.wv.most_similar(positive='transformation', topn=5)
|
75 |
-
|
76 |
# get dissimilar phrases
|
77 |
model.wv.most_similar(negative='transformation', topn=5, restrict_vocab=None)
|
78 |
-
|
79 |
# compute pairwise similarity scores (distance = 1 - similarity)
|
80 |
model.wv.similarity('transformation', 'continuity')
|
81 |
```
|
|
|
22 |
|
23 |
# EarningsCall2Vec
|
24 |
|
25 |
+
**EarningsCall2Vec** is a [fastText](https://fasttext.cc/) word embedding model that was trained via [Gensim](https://radimrehurek.com/gensim/). It maps each token in the vocabulary to a dense, 300-dimensional vector space, designed for performing **semantic search**. More details about the training procedure can be found [below](#model-training).
|
26 |
|
27 |
|
28 |
## Background
|
|
|
69 |
|
70 |
# extract word embeddings
|
71 |
model.wv['transformation']
|
|
|
72 |
# get similar phrases
|
73 |
model.wv.most_similar(positive='transformation', topn=5)
|
|
|
74 |
# get dissimilar phrases
|
75 |
model.wv.most_similar(negative='transformation', topn=5, restrict_vocab=None)
|
|
|
76 |
# compute pairwise similarity scores (distance = 1 - similarity)
|
77 |
model.wv.similarity('transformation', 'continuity')
|
78 |
```
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|