language:
- en
library_name: fasttext
pipeline_tag: text-classification
tags:
- text
- semantic-similarity
- earnings-call-transcripts
- word2vec
- fasttext
widget:
- text: transformation
example_title: transformation
- text: sustainability
example_title: sustainability
- text: turnaround
example_title: turnaround
- text: disruption
example_title: disruption
EarningsCall2Vec
This is a fastText model trained via Gensim: It maps each token in the vocabulary (i.e., unigram and frequently coocurring bi-, tri-, and fourgrams) to a dense, 300-dimensional vector space, designed for performing semantic search. It has been trained on corpus of ~160k earning call transcripts, in particular the executive remarks within the Q&A-section of these transcripts (13m sentences).
Usage (API)
pip install -U xxx
Then you can use the model like this:
py code
Usage (Gensim)
pip install -U xxx
Then you can use the model like this:
py code
Background
Context on the project.
Intended Uses
Our model is intented to be used for semantic search on a token-level: It encodes search-queries (i.e., token) in a dense vector space and finds semantic neighbours, i.e., token which frequently occur within similar contexts in the underlying training data. Note that this search is only feasible for individual token and may produce deficient results in the case of out-of-vocabulary token.
Training procedure
logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.INFO)
# init
model = FastText(
vector_size=300,
window=5,
min_count=10,
alpha=0.025,
negative = 5,
seed=2021,
sample = 0.001,
sg=1,
hs=0,
max_vocab_size=None,
workers=10,
)
# build vocab
model.build_vocab(corpus_iterable=LineSentence(<PATH_TRAIN_DATA>))
# train model
model.train(
corpus_iterable=LineSentence(<PATH_TRAIN_DATA>),
total_words=model.corpus_total_words,
total_examples=model.corpus_count,
epochs=50,
)
# save to binary format
save_facebook_model(<PATH_MOD_SAVE>)
Training Data
description