papers AI Learner
The Github is limit! Click to go to the new site.

Neural Transductive Learning and Beyond: Morphological Generation in the Minimal-Resource Setting

2019-05-09
Katharina Kann, Hinrich Schütze

Abstract

Neural state-of-the-art sequence-to-sequence (seq2seq) models often do not perform well for small training sets. We address paradigm completion, the morphological task of, given a partial paradigm, generating all missing forms. We propose two new methods for the minimal-resource setting: (i) Paradigm transduction: Since we assume only few paradigms available for training, neural seq2seq models are able to capture relationships between paradigm cells, but are tied to the idiosyncracies of the training set. Paradigm transduction mitigates this problem by exploiting the input subset of inflected forms at test time. (ii) Source selection with high precision (SHIP): Multi-source models which learn to automatically select one or multiple sources to predict a target inflection do not perform well in the minimal-resource setting. SHIP is an alternative to identify a reliable source if training data is limited. On a 52-language benchmark dataset, we outperform the previous state of the art by up to 9.71% absolute accuracy.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1809.08733

PDF

http://arxiv.org/pdf/1809.08733


Similar Posts

Comments