Learning Kernels over Strings using Gaussian Processes

Daniel Beck, Trevor Cohn


Abstract
Non-contiguous word sequences are widely known to be important in modelling natural language. However they not explicitly encoded in common text representations. In this work we propose a model for text processing using string kernels, capable of flexibly representing non-contiguous sequences. Specifically, we derive a vectorised version of the string kernel algorithm and their gradients, allowing efficient hyperparameter optimisation as part of a Gaussian Process framework. Experiments on synthetic data and text regression for emotion analysis show the promise of this technique.
Anthology ID:
I17-2012
Volume:
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
Month:
November
Year:
2017
Address:
Taipei, Taiwan
Venue:
IJCNLP
SIG:
Publisher:
Asian Federation of Natural Language Processing
Note:
Pages:
67–73
Language:
URL:
https://www.aclweb.org/anthology/I17-2012
DOI:
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/I17-2012.pdf
Note:
 I17-2012.Notes.pdf