Zero-shot Reading Comprehension by Cross-lingual Transfer Learning with Multi-lingual Language Representation Model

09/15/2019
by   Tsung-Yuan Hsu, et al.
0

Because it is not feasible to collect training data for every language, there is a growing interest in cross-lingual transfer learning. In this paper, we systematically explore zero-shot cross-lingual transfer learning on reading comprehension tasks with a language representation model pre-trained on multi-lingual corpus. The experimental results show that with pre-trained language representation zero-shot learning is feasible, and translating the source data into the target language is not necessary and even degrades the performance. We further explore what does the model learn in zero-shot setting.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 4

05/08/2021

Improving Cross-Lingual Reading Comprehension with Self-Training

Substantial improvements have been made in machine reading comprehension...
06/03/2021

Bilingual Alignment Pre-training for Zero-shot Cross-lingual Transfer

Multilingual pre-trained models have achieved remarkable transfer perfor...
04/17/2021

Improving Zero-Shot Cross-Lingual Transfer Learning via Robust Training

In recent years, pre-trained multilingual language models, such as multi...
01/26/2021

Analyzing Zero-shot Cross-lingual Transfer in Supervised NLP Tasks

In zero-shot cross-lingual transfer, a supervised NLP task trained on a ...
04/16/2020

Cross-lingual Contextualized Topic Models with Zero-shot Learning

Many data sets in a domain (reviews, forums, news, etc.) exist in parall...
12/01/2021

Zero-Shot Cross-Lingual Machine Reading Comprehension via Inter-Sentence Dependency Graph

We target the task of cross-lingual Machine Reading Comprehension (MRC) ...
09/23/2020

Worst-Case-Aware Curriculum Learning for Zero and Few Shot Transfer

Multi-task transfer learning based on pre-trained language encoders achi...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.