Paper Info
Title
Exploring phrase-compositionality in skip-gram models.
Abstract
In this paper, we introduce a variation of the skip-gram model which jointly learns distributed word vector representations and their way of composing to form phrase embeddings. In particular, we propose a learning procedure that incorporates a phrase-compositionality function which can capture how we want to compose phrases vectors from their component word vectors. Our experiments show improvement in word and phrase similarity tasks as well as syntactic tasks like dependency parsing using the proposed joint models.
Year
Venue
Field
2016
arXiv: Computation and Language
Principle of compositionality,Computer science,Phrase,Speech recognition,Dependency grammar,Natural language processing,Artificial intelligence,Gram,Syntax,Machine learning
DocType
Volume
Citations 
Journal
abs/1607.06208
0
PageRank 
References 
Authors
0.34
14
2
Name
Order
Citations
PageRank
Xiaochang Peng1545.31
Daniel Gildea22269193.43