UNL-French deconversion as transfer & generation from an interlingua with possible quality enhancement through offline human interaction

TL;DR

This paper introduces the UNL-French deconverter architecture that generates French from UNL interlingua, utilizing transfer and generation techniques, with potential quality improvements through offline human interaction for iterative learning.

Contribution

It presents a novel deconversion system from UNL to French that incorporates interaction-based quality enhancement and discusses embedding interaction in the post-editing phase.

Findings

Interaction improves deconversion quality

Offline interaction can enhance future output quality

System integrates classical transfer with UNL-specific tools

Abstract

We present the architecture of the UNL-French deconverter, which "generates" from the UNL interlingua by first"localizing" the UNL form for French, within UNL, and then applying slightly adapted but classical transfer and generation techniques, implemented in GETA's Ariane-G5 environment, supplemented by some UNL-specific tools. Online interaction can be used during deconversion to enhance output quality and is now used for development purposes. We show how interaction could be delayed and embedded in the postedition phase, which would then interact not directly with the output text, but indirectly with several components of the deconverter. Interacting online or offline can improve the quality not only of the utterance at hand, but also of the utterances processed later, as various preferences may be automatically changed to let the deconverter "learn".