Machine Translation in Pronunciation Space

TL;DR

This paper explores direct translation in pronunciation space, comparing it with traditional text translation, and finds that all methods perform similarly, suggesting pronunciation-based translation could be a viable alternative.

Contribution

It introduces three new pronunciation-based translation categories and provides large-scale experimental evidence of their effectiveness compared to traditional text translation.

Findings

All four translation categories have comparable performance.

Pronunciation space translation can be as effective as text-based translation.

Experiments conducted on a large dataset with 20 million pairs.

Abstract

The research in machine translation community focus on translation in text space. However, humans are in fact also good at direct translation in pronunciation space. Some existing translation systems, such as simultaneous machine translation, are inherently more natural and thus potentially more robust by directly translating in pronunciation space. In this paper, we conduct large scale experiments on a self-built dataset with about $20$M En-Zh pairs of text sentences and corresponding pronunciation sentences. We proposed three new categories of translations: $1)$ translating a pronunciation sentence in source language into a pronunciation sentence in target language (P2P-Tran), $2)$ translating a text sentence in source language into a pronunciation sentence in target language (T2P-Tran), and $3)$ translating a pronunciation sentence in source language into a text sentence in target language (P2T-Tran), and compare them with traditional text translation (T2T-Tran). Our experiments clearly show that all $4$ categories of translations have comparable performances, with small and sometimes ignorable differences.