Selectional preference embeddings (EMNLP 2017)
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...
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Dokumenttyp: | Datenbank Forschungsdaten |
| Sprache: | Englisch |
| Veröffentlicht: |
Heidelberg
Universität
2019-01-31
|
| DOI: | 10.11588/data/FJQ4XL |
| Schlagworte: | |
| Online-Zugang: | Verlag, kostenfrei, Volltext: http://dx.doi.org/10.11588/data/FJQ4XL Verlag, kostenfrei, Volltext: https://heidata.uni-heidelberg.de/dataset.xhtml?persistentId=doi:10.11588/data/FJQ4XL 
|
| Verfasserangaben: | Benjamin Heinzerling |
| Zusammenfassung: | 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) |
|---|---|
| Beschreibung: | Gesehen am 21.02.2019 |
| Beschreibung: | Online Resource |
| DOI: | 10.11588/data/FJQ4XL |