Harnessing Multilingual Resources to Question Answering in Arabic
This work addresses the challenge of limited training data for Arabic question answering in a religious context, representing an incremental improvement by adapting existing multilingual methods to a specific domain.
The paper tackles the problem of question answering in Arabic using the Qur'an as a domain-specific dataset, where the model predicts answer spans within passages. The result is a two-step BERT-based approach that leverages multilingual resources and a crawled Arabic corpus to address data scarcity, achieving improved performance through candidate generation and ranking.
The goal of the paper is to predict answers to questions given a passage of Qur'an. The answers are always found in the passage, so the task of the model is to predict where an answer starts and where it ends. As the initial data set is rather small for training, we make use of multilingual BERT so that we can augment the training data by using data available for languages other than Arabic. Furthermore, we crawl a large Arabic corpus that is domain specific to religious discourse. Our approach consists of two steps, first we train a BERT model to predict a set of possible answers in a passage. Finally, we use another BERT based model to rank the candidate answers produced by the first BERT model.