Multilingual Extractive Reading Comprehension by Runtime Machine Translation

By Akari Asai, Akiko Eriguchi, Kazuma Hashimoto, Yoshimasa Tsuruoka. 2018

61 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing, Evaluation & Benchmarks

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Natural Language Processing

In Evaluation & Benchmarks

Citations in the corpus

TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages (2020, methodology): “, 2018) in Chinese, French/Japanese evaluation sets for SQuAD created via translation (Asai et al., 2018), Korean translations of SQuAD (Lee et al.”
MLQA: Evaluating Cross-lingual Extractive Question Answering (2019, background): “Recognising this need, several cross-lingual datasets have recently been assembled (Asai et al., 2018; Liu et al., 2019a).”
Beyond English-Only Reading Comprehension: Experiments in Zero-shot Multilingual Transfer for Bulgarian (2019, methodology): “A similar idea was applied to MRC by Asai et al. (2018), who translated each question to a pivot language, and then found the correct answer in the target language using soft-alignment attention scores.”
Zero-shot Reading Comprehension by Cross-lingual Transfer Learning with Multi-lingual Language Representation Model (2019, unknown): “Existing methods (Asai et al., 2018) of crosslingual transfer learning on RC datasets often count on machine translation (MT) to translate data from source language into target language, or vice versa.”
XLDA: Cross-Lingual Data Augmentation for Natural Language Inference and Question Answering (2019, result): “This is in keeping with the ﬁndings of Asai et al. (2018), which show that the ability to correctly translate questions is crucial for question answering.”
Learning with Limited Data for Multilingual Reading Comprehension (2019, methodology): “For example, (passage p , question q , answer a ) in SQuAD can be translated into ( p (cid:48) , q (cid:48) , a (cid:48) ) in a target language (Asai et al., 2018; Lee et al., 2018).”
Cross-Lingual Transfer Learning for Question Answering (2019, methodology): “Using MT to achieve knowledge transfer between different languages has been studied on sentiment analysis (Moham-mad et al., 2016), spoken language understanding (Stepanov et al., 2013; Schuster et al., 2018) and question answer (Asai et al., 2018).”
Cross-Lingual Machine Reading Comprehension (2019, methodology): “To build a simple cross-lingual machine reading comprehension system, it is straightforward to utilize translation system to bridge source and target language (Asai et al., 2018).”
Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model (2024, methodology): “Translate-train, translate-test (Asai et al., 2018; Cui et al., 2019; Jundi and Lapesa, 2022), or language pivots (Montero et al., 2022) are common techniques employing translation models to bridge language gaps between the model and its target language.”