Login | Deutsch
  • TU
  • |
  • ULB
  • |
  • TUdata
    • English
    • Deutsch (Deutschland)
  •   Documents
  •   FAQs
  •   Browse
    • All of TUdatalib
    • Communities
    • Titles
    • Authors
    • Type
    • By Submit Date
    • Subjects
    • DFG subject classifications
    • This Context
    • Titles
    • Authors
    • Type
    • By Submit Date
    • Subjects
    • DFG subject classifications
View Item 
  •   TUdatalib Home
  • Technische Universität Darmstadt
  • Forschungskooperationen
  • AIPHES Heidelberg
  • View Item
  •   TUdatalib Home
  • Technische Universität Darmstadt
  • Forschungskooperationen
  • AIPHES Heidelberg
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Browse

All of TUdatalibCommunitiesTitlesAuthorsTypeBy Submit DateSubjectsDFG subject classificationsThis CollectionTitlesAuthorsTypeBy Submit DateSubjectsDFG subject classifications

My Account

LoginRegister

Statistics

View Usage Statistics

Selectional Preference Embeddings (EMNLP 2017)

Thumbnail
Author
Heinzerling, Benjamin
Metadata
Show full item record
Export
Text
BibTex
DataCite XML
JSON

Description

Joint embeddings of selectional preferences, words, and fine-grained entity types.

The vocabulary consists of:

  • verbs and their dependency relation separated by "@", e.g. "sink@nsubj" or "elect@dobj"
  • words and short noun phrases, e.g. "Titanic"
  • fine-grained entity types using the FIGER inventory, e.g.: /product/ship or /person/politician

The files are in word2vec binary format, which can be loaded in Python with gensim like this:

from gensim.models import KeyedVectors

emb_file = "/path/to/embedding_file"
emb = KeyedVectors.load_word2vec_format(emb_file, binary=True)

Subject

Computer and Information Science

URI

https://doi.org/10.11588/data/FJQ4XL

Collections

  • AIPHES Heidelberg [5]
Legal note | About TUdatalib | Contact | Privacy Policy | Agreement | Website analytics | OAI-PMH | Changelog
 

 

Legal note | About TUdatalib | Contact | Privacy Policy | Agreement | Website analytics | OAI-PMH | Changelog