-
Enhancing Answer Boundary Detection for Multilingual Machine Reading Comprehension
Multilingual pre-trained models could leverage the training data from a ...
read it
-
Cross-Lingual Machine Reading Comprehension
Though the community has made great progress on Machine Reading Comprehe...
read it
-
XCMRC: Evaluating Cross-lingual Machine Reading Comprehension
We present XCMRC, the first public cross-lingual language understanding ...
read it
-
Multilingual Synthetic Question and Answer Generation for Cross-Lingual Reading Comprehension
We propose a simple method to generate large amounts of multilingual que...
read it
-
Adversarial Augmentation Policy Search for Domain and Cross-Lingual Generalization in Reading Comprehension
Reading comprehension models often overfit to nuances of training datase...
read it
-
Reading Comprehension in Czech via Machine Translation and Cross-lingual Transfer
Reading comprehension is a well studied task, with huge training dataset...
read it
-
Improved Synthetic Training for Reading Comprehension
Automatically generated synthetic training examples have been shown to i...
read it
Cross-lingual Machine Reading Comprehension with Language Branch Knowledge Distillation
Cross-lingual Machine Reading Comprehension (CLMRC) remains a challenging problem due to the lack of large-scale annotated datasets in low-source languages, such as Arabic, Hindi, and Vietnamese. Many previous approaches use translation data by translating from a rich-source language, such as English, to low-source languages as auxiliary supervision. However, how to effectively leverage translation data and reduce the impact of noise introduced by translation remains onerous. In this paper, we tackle this challenge and enhance the cross-lingual transferring performance by a novel augmentation approach named Language Branch Machine Reading Comprehension (LBMRC). A language branch is a group of passages in one single language paired with questions in all target languages. We train multiple machine reading comprehension (MRC) models proficient in individual language based on LBMRC. Then, we devise a multilingual distillation approach to amalgamate knowledge from multiple language branch models to a single model for all target languages. Combining the LBMRC and multilingual distillation can be more robust to the data noises, therefore, improving the model's cross-lingual ability. Meanwhile, the produced single multilingual model is applicable to all target languages, which saves the cost of training, inference, and maintenance for multiple models. Extensive experiments on two CLMRC benchmarks clearly show the effectiveness of our proposed method.
READ FULL TEXT
Comments
There are no comments yet.