Improving Low resource Reading Comprehension via Cross lingual Transposition Rethinking

Abstract

Extractive Question Answering (QA) has made tremendous advances enabled by the availability of large scale high quality QA training data. Although such rapid progress and widespread application, extractive QA datasets in languages other than English remain scarce. Moreover, collecting such a sufficient amount of training data for each language is costly and even impossible. To address this issue, we propose a Cross Lingual Transposition ReThinking (XLTT) model by modelling existing high quality extractive reading comprehension datasets in a multilingual environment. To be specific, we present multilingual adaptive attention (MAA) to combine intra attention and inter attention to learn more general generalizable semantic and lexical knowledge from each pair of language families. Furthermore, to make full use of existing datasets, we adopt a new training framework to train our model by calculating task level similarities between each existing dataset and target dataset. The experimental results show that our XLTT model surpasses six baselines on two multilingual ERC benchmarks, especially more effective for low resource languages with 3.9 and 4.1 average improvement in F1 and EM, respectively.