Applying Multilingual Models to Question Answering (QA)

2022/12/04 by Joaquin, Ayrton San, Skubacz, Filip
#Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2212.01933

Abstract

We study the performance of monolingual and multilingual language models on the task of question-answering (QA) on three diverse languages: English, Finnish and Japanese. We develop models for the tasks of (1) determining if a question is answerable given the context and (2) identifying the answer texts within the context using IOB tagging. Furthermore, we attempt to evaluate the effectiveness of a pre-trained multilingual encoder (Multilingual BERT) on cross-language zero-shot learning for both the answerability and IOB sequence classifiers.

Related

• MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answering
• Multilingual Question Answering from Formatted Text applied to Conversational Agents
• Learning to Answer Multilingual and Code-Mixed Questions
• Investigating Post-pretraining Representation Alignment for Cross-Lingual Question Answering
• MLQA: Evaluating Cross-lingual Extractive Question Answering