Multilingual Extractive Reading Comprehension by Runtime Machine Translation

TL;DR

This paper presents a novel multilingual extractive reading comprehension system that leverages neural machine translation and existing English RC models to perform RC in languages without training data, demonstrated on Japanese and French.

Contribution

The work introduces the first RC approach for languages lacking training data by combining neural machine translation with English RC models.

Findings

Significantly outperforms back-translation baseline

Effective in Japanese and French RC tasks

Demonstrates feasibility of multilingual RC without language-specific training data

Abstract

Despite recent work in Reading Comprehension (RC), progress has been mostly limited to English due to the lack of large-scale datasets in other languages. In this work, we introduce the first RC system for languages without RC training data. Given a target language without RC training data and a pivot language with RC training data (e.g. English), our method leverages existing RC resources in the pivot language by combining a competitive RC model in the pivot language with an attentive Neural Machine Translation (NMT) model. We first translate the data from the target to the pivot language, and then obtain an answer using the RC model in the pivot language. Finally, we recover the corresponding answer in the original language using soft-alignment attention scores from the NMT model. We create evaluation sets of RC data in two non-English languages, namely Japanese and French, to evaluate our method. Experimental results on these datasets show that our method significantly outperforms a back-translation baseline of a state-of-the-art product-level machine translation system.