View on GitHub

Research Review Notes

Summaries of academic research papers

Multi-space Variational Encoder-Decoders for Semi-supervised Labeled Sequence Transduction

Idea

The general idea seems similar to style-transfer in text. Labeled sequence transduction is just a roundabout way of saying that a source text $x^{(s)}$ is to be transformed into a target text $x^{(t)}$ such that $x^{(t)}$ is conditioned on the labels $y^{(t)}$.

Background

The morphological re-inflection problem tries to change a sequence of characters of an inflected word. For example, convert ‘playing’ into ‘played’, given a set of labels $y^{(t)}$ such that $y^{(t)}_{pos}=\text{verb}$ and $y^{(t)}_{tense}=\text{past}$

Method

Observations