Where academic tradition
meets the exciting future

Post-hoc Manipulations of Vector Space Models with Application to Semantic Role Labeling

Jenna Kanerva, Filip Ginter, Post-hoc Manipulations of Vector Space Models with Application to Semantic Role Labeling . In: Alexandre Allauzen, Raffaella Bernardi, Edward Grefenstette, Hugo Larochelle, Christopher Manning, Scott Wen-tau Yih (Eds.), Proceedings of the 2nd Workshop on Continuous Vector Space Models and their Compositionality (CVSC) , 1–10, Association for Computational Linguistics, 2014.

Abstract:

In this paper, we introduce several vector
space manipulation methods that are ap-
plied to trained vector space models in a
post-hoc fashion, and present an applica-
tion of these techniques in semantic role
labeling for Finnish and English. Specifi-
cally, we show that the vectors can be cir-
cularly shifted to encode syntactic infor-
mation and subsequently averaged to pro-
duce representations of predicate senses
and arguments. Further, we show that it is
possible to effectively learn a linear trans-
formation between the vector representa-
tions of predicates and their arguments,
within the same vector space.

BibTeX entry:

@INPROCEEDINGS{inpKaGi14a,
  title = {Post-hoc Manipulations of Vector Space Models with Application to Semantic Role Labeling },
  booktitle = { Proceedings of the 2nd Workshop on Continuous Vector Space Models and their Compositionality (CVSC) },
  author = {Kanerva, Jenna and Ginter, Filip},
  editor = {Allauzen, Alexandre and Bernardi, Raffaella and Grefenstette, Edward and Larochelle, Hugo and Manning, Christopher and Yih, Scott Wen-tau},
  publisher = {Association for Computational Linguistics},
  pages = {1–10},
  year = {2014},
}

Belongs to TUCS Research Unit(s): Turku BioNLP Group

Edit publication