Explicit Retrofitting of Distributional Word Vectors

Explore this paper's citation graph

Summary

This work transforms external lexico-semantic relations into training examples which are used to learn an explicit retrofitting model (ER), which allows us to learn a global specialization function and specialize the vectors of words unobserved in the training data as well.

Type
article
Published
2018-01-01
Cited by
77
References
61
Access
Open access

Keywords

Retrofitting, Computer science, Word (group theory), Natural language processing, Distributional semantics

References

Cited by

Related papers