Show HN: Wikipedia2Vec – A tool for learning embeddings of words and entities
wikipedia2vec.github.io
Show HN: Wikipedia2Vec – A tool for learning embeddings of words and entities
1–10 of 17 posts
Re: Show HN: Wikipedia2Vec – A tool for learning embeddings of words and entities
#2This is awesome! Is there a plan to support all the major embedding algorithms?
Re: Show HN: Wikipedia2Vec – A tool for learning embeddings of words and entities
#3Its name is misleading. It's word2vec based on Wikipedia words, not - vectors for Wikipedia pages (cf node2vec, food2vec, game2vec, etc).
Re: Show HN: Wikipedia2Vec – A tool for learning embeddings of words and entities
#4Its name is misleading. It's word2vec based on Wikipedia words, not - vectors for Wikipedia pages (cf node2vec, food2vec, game2vec, etc).
Please note that similar to other approaches (e.g., node2vec), Wikipedia2Vec learns embeddings for Wikipedia entities in addition to embeddings for words.
Re: Show HN: Wikipedia2Vec – A tool for learning embeddings of words and entities
#5If you're wondering what the point of this is when word2vec
wikipedia pre-trained embeddings are already easily found
>Wikipedia2Vec is based on the Word2vec's skip-gram model that learns to predict neighboring words given each word in corpora. We extend the skip-gram model by adding the following two submodels:
>The link graph model that learns to estimate neighboring entities given an entity in the link graph of Wikipedia entities.
>The anchor context model that learns to predict neighboring words given an entity by using a link that points to the entity and its neighboring words.
>By jointly optimizing the skip-gram model and these two submodels, our model simultaneously learns the embedding of words and entities from Wikipedia. For further details, please refer to our paper: Joint Learning of the Embedding of Words and Entities for Named Entity Disambiguation.
Re: Show HN: Wikipedia2Vec – A tool for learning embeddings of words and entities
#6Curious if there are any benchmarks against Fasttext, Elmo, etc..
Re: Show HN: Wikipedia2Vec – A tool for learning embeddings of words and entities
#7How portable are tools like these among different ontologies/knowledge bases?
Re: Show HN: Wikipedia2Vec – A tool for learning embeddings of words and entities
#8Is there any obvious reason why all entities that have a wikipedia article associated with them don't appear as entities in this output?
Re: Show HN: Wikipedia2Vec – A tool for learning embeddings of words and entities
#9Is there any obvious reason why all entities that have a wikipedia article associated with them don't appear as entities in this output?
What kind of output did you mean? Wikipedia2Vec learns embeddings of entities which have links from other articles more than min-entity-count times.
Re: Show HN: Wikipedia2Vec – A tool for learning embeddings of words and entities
#10How portable are tools like these among different ontologies/knowledge bases?
The current code is written specifically for Wikipedia. However, its algorithm is portable for knowledge bases that contains articles and their entity annotations.