Giter Site home page Giter Site logo

hypere's People

Contributors

belizgunel avatar fredsala avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar

hypere's Issues

How were these embeddings trained?

Is there software available to fit these kind of hyperbolic embeddings on our own datasets? If not, could you explain a little what the training procedure looks like?

Thanks!
~ Ben

Demo NameError: name 'make_edge_set' is not defined

I'm trying to run the demo HyperE_demo.ipynb in a Jupyter Notebook. I have installed the dependencies and downloaded the wordnet NLTK data.

Running the notebook works up to the cell that begins with the comment "Creating the edge list for hypernym relationship in Wordnet." It fails with the following error:

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-10-e8a28bbcc444> in <module>
     24 
     25 
---> 26 SynstoIDs, IDstoSyns, X, all_syns = load_wordnet()
     27 G = nx.from_scipy_sparse_matrix(X)
     28 Gc = max(nx.connected_component_subgraphs(G), key=len)

<ipython-input-10-e8a28bbcc444> in load_wordnet()
     11 
     12     n = len(all_syns)
---> 13     e = make_edge_set()
     14 
     15     for idx, x in enumerate(all_syns):

NameError: name 'make_edge_set' is not defined

Where is make_edge_set() defined?

Embedding key mapping

Hello, first of all thanks for this great work!

I have a question regarding the wordnet embeddings such as hypernym_noun.50d.txt.

For example the key screwdriver has two different senses in wordnet:
[Synset('screwdriver.n.01'), Synset('screwdriver.n.02')]

  • Do you have some kind of mapping?
  • How are the embedding keys and the wordnet senses related?

Thanks!

How were the UMLS embeddings acquired based on ICD?

Thanks for sharing the embeddings.

In http://hazyresearch.stanford.edu/hyperE/ it says UMLS embeddings were based on the "Diagnostic hierarchy from ICD-9-CM and ICD-10-CM vocabularies of UMLS". The shared files actually contain a vector for each CUI, instead of ICD code. I wonder how a matching between UMLS and ICD-9-CM was established, and are ICD-9-CM embedding directly available? Many thanks!

Best wishes,
A

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.