Multilingual Extractive Reading Comprehension by Runtime Machine Translation

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.

References in corpus (12)

• Improving neural networks by preventing co-adaptation of feature detectors
• Teaching Machines to Read and Comprehend
• On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
• SQuAD: 100,000+ Questions for Machine Comprehension of Text
• Effective Approaches to Attention-based Neural Machine Translation
• QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension
• Adversarial Examples for Evaluating Reading Comprehension Systems
• Modeling Coverage for Neural Machine Translation
• DCN+: Mixed Objective and Deep Residual Coattention for Question Answering
• DuReader: a Chinese Machine Reading Comprehension Dataset from Real-world Applications
• Making Neural QA as Simple as Possible but not Simpler
• Exploring Question Understanding and Adaptation in Neural-Network-Based Question Answering

Cited by in corpus (16)

• QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension
• XLDA: Cross-Lingual Data Augmentation for Natural Language Inference and Question Answering
• Cross-Lingual Machine Reading Comprehension
• TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages
• Zero-shot Reading Comprehension by Cross-lingual Transfer Learning with Multi-lingual Language Representation Model
• FQuAD: French Question Answering Dataset
• Multilingual Question Answering from Formatted Text applied to Conversational Agents
• A Survey on Machine Reading Comprehension: Tasks, Evaluation Metrics and Benchmark Datasets
• Cross-Lingual Transfer Learning for Question Answering
• Enhancing Answer Boundary Detection for Multilingual Machine Reading Comprehension
• Beyond English-Only Reading Comprehension: Experiments in Zero-Shot Multilingual Transfer for Bulgarian
• XOR QA: Cross-lingual Open-Retrieval Question Answering
• Cross-lingual Machine Reading Comprehension with Language Branch Knowledge Distillation
• Are Multilingual BERT models robust? A Case Study on Adversarial Attacks for Multilingual Question Answering
• A Multilingual Modeling Method for Span-Extraction Reading Comprehension
• BiPaR: A Bilingual Parallel Dataset for Multilingual and Cross-lingual Reading Comprehension on Novels