Unsupervised Neural Dialect Translation with Commonality and Diversity Modeling

TL;DR

This paper proposes an unsupervised neural dialect translation approach that leverages commonality and diversity modeling to effectively translate between dialects using only monolingual data, outperforming traditional methods.

Contribution

It introduces a novel framework exploiting commonality and diversity in dialects through pivot-private embeddings, layer coordination, and parameter sharing, specifically for unsupervised translation.

Findings

Outperforms rule-based Chinese conversion by over 12 BLEU scores.

Effectively models dialectal commonality and diversity.

Uses large monolingual datasets for Mandarin and Cantonese.

Abstract

As a special machine translation task, dialect translation has two main characteristics: 1) lack of parallel training corpus; and 2) possessing similar grammar between two sides of the translation. In this paper, we investigate how to exploit the commonality and diversity between dialects thus to build unsupervised translation models merely accessing to monolingual data. Specifically, we leverage pivot-private embedding, layer coordination, as well as parameter sharing to sufficiently model commonality and diversity among source and target, ranging from lexical, through syntactic, to semantic levels. In order to examine the effectiveness of the proposed models, we collect 20 million monolingual corpus for each of Mandarin and Cantonese, which are official language and the most widely used dialect in China. Experimental results reveal that our methods outperform rule-based simplified and traditional Chinese conversion and conventional unsupervised translation models over 12 BLEU scores.