English

Extrapolation in NLP

Computation and Language 2018-05-18 v1

Abstract

We argue that extrapolation to examples outside the training space will often be easier for models that capture global structures, rather than just maximise their local fit to the training data. We show that this is true for two popular models: the Decomposable Attention Model and word2vec.

Keywords

Cite

@article{arxiv.1805.06648,
  title  = {Extrapolation in NLP},
  author = {Jeff Mitchell and Pasquale Minervini and Pontus Stenetorp and Sebastian Riedel},
  journal= {arXiv preprint arXiv:1805.06648},
  year   = {2018}
}
R2 v1 2026-06-23T01:58:26.093Z