Audience-specific Explanations for Machine Translation

TL;DR

This paper introduces a semi-automatic method to extract explanations for culturally sensitive words in machine translation, improving the creation of explanation datasets across multiple language pairs.

Contribution

It proposes a novel semi-automatic technique to extract explanations from large parallel corpora, addressing data sparsity issues in creating explanation datasets for machine translation.

Findings

Over 10% of sentences contain explanations after extraction

Original sentences with explanations are only 1.9%

Method is robust across English-German, English-French, and English-Chinese pairs

Abstract

In machine translation, a common problem is that the translation of certain words even if translated can cause incomprehension of the target language audience due to different cultural backgrounds. A solution to solve this problem is to add explanations for these words. In a first step, we therefore need to identify these words or phrases. In this work we explore techniques to extract example explanations from a parallel corpus. However, the sparsity of sentences containing words that need to be explained makes building the training dataset extremely difficult. In this work, we propose a semi-automatic technique to extract these explanations from a large parallel corpus. Experiments on English->German language pair show that our method is able to extract sentence so that more than 10% of the sentences contain explanation, while only 1.9% of the original sentences contain explanations. In addition, experiments on English->French and English->Chinese language pairs also show similar conclusions. This is therefore an essential first automatic step to create a explanation dataset. Furthermore we show that the technique is robust for all three language pairs.