Machine translation of low-resource spoken dialects : strategies for normalizing swiss german

Honnet, Pierre-Edouard (Telepathy Labs, Zürich, Switzerland) ; Popescu-Belis, Andrei (School of Management and Engineering Vaud, HES-SO // University of Applied Sciences Western Switzerland) ; Musat, Claudiu (Swisscom (Schweiz) AG, Bern, Switzerland) ; Baeriswyl, Michael (Swisscom (Schweiz) AG, Bern, Switzerland)

The goal of this work is to design a machine translation (MT) system for a low-resource family of dialects, collectively known as Swiss German, which are widely spoken in Switzerland but seldom written. We collected a significant number of parallel written resources to start with, up to a total of about 60k words. Moreover, we identified several other promising data sources for Swiss German. Then, we designed and compared three strategies for normalizing Swiss German input in order to address the regional diversity. We found that character-based neural MT was the best solution for text normalization. In combination with phrase-based statistical MT, our solution reached 36% BLEU score when translating from the Bernese dialect. This value, however, decreases as the testing data becomes more remote from the training one, geographically and topically. These resources and normalization techniques are a first step towards full MT of Swiss German dialects.

Adresse bibliogr.:
Miyazaki, Japan, 7-12 May 2018
8 pages
Le document apparaît dans:

Note: The status of this file is: restricted

 Notice créée le 2018-05-22, modifiée le 2018-12-20

Télécharger le document

Évaluer ce document:

Rate this document:
(Pas encore évalué)