Statements (60)
| Predicate | Object |
|---|---|
| gptkbp:instance_of |
gptkb:Artificial_Intelligence
|
| gptkbp:bfsLayer |
4
|
| gptkbp:bfsParent |
gptkb:Gensim
|
| gptkbp:applies_to |
unsupervised learning
sentiment analysis |
| gptkbp:based_on |
gptkb:Word2_Vec
|
| gptkbp:benefits |
gptkb:academic_research
gptkb:film_production_company data representation information extraction question answering data mining entity recognition semantic search feature extraction text generation language modeling customer feedback analysis text summarization social media analysis content recommendation user profiling text analytics document clustering knowledge graph construction |
| gptkbp:can_be_used_with |
other embedding techniques
|
| gptkbp:developed_by |
Tomas Mikolov
|
| gptkbp:enables |
semantic similarity measurement
|
| https://www.w3.org/2000/01/rdf-schema#label |
Doc2 Vec
|
| gptkbp:improves |
text classification
|
| gptkbp:input_output |
fixed-size vectors
|
| gptkbp:is_adopted_by |
gptkb:film_production_company
|
| gptkbp:is_compared_to |
gptkb:software
TF-IDF |
| gptkbp:is_evaluated_by |
cosine similarity
extrinsic evaluation intrinsic evaluation downstream tasks |
| gptkbp:is_implemented_in |
gptkb:Gensim
gptkb:Library |
| gptkbp:is_influenced_by |
gptkb:microprocessor
|
| gptkbp:is_part_of |
gptkb:software_framework
NLP toolkit |
| gptkbp:is_popular_in |
text mining
|
| gptkbp:is_related_to |
deep learning
|
| gptkbp:is_similar_to |
Paragraph Vector
|
| gptkbp:is_used_by |
gptkb:physicist
|
| gptkbp:is_used_for |
natural language processing
topic modeling |
| gptkbp:is_used_in |
search engines
chatbots information retrieval recommendation systems |
| gptkbp:provides |
vector representations of documents
|
| gptkbp:release_year |
gptkb:2014
|
| gptkbp:represents |
variable-length documents
|
| gptkbp:requires |
large datasets
|
| gptkbp:training |
unlabeled data
skip-gram model CBOW model |