Zero-shot Reading Comprehension by Cross-lingual Transfer Learning with Multi-lingual Language Representation Model
By Chi-Liang Liu, Hung-yi Lee. 2019
60 citations recorded by the source corpus.
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 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.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing, Question Answering & Reading Comprehension
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Graham Neubig
- Orhan Firat
- Melvin Johnson
- Sebastian Ruder
- Junjie Hu
- Aditya Siddhant
- Ivan Vulic
- Felix Stahlberg
In Computer Vision and Pattern Recognition
- Graham Neubig
- Orhan Firat
- Melvin Johnson
- Sebastian Ruder
- Aditya Siddhant
- Junjie Hu
- Ivan Vulic
- Felix Stahlberg
In Natural Language Processing
- Graham Neubig
- Orhan Firat
- Melvin Johnson
- Sebastian Ruder
- Junjie Hu
- Aditya Siddhant
- Felix Stahlberg
- Ankur Bapna
In Question Answering & Reading Comprehension
Citations in the corpus
- XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization (2020, background): “If this fails, as a back-off we fuzzy match the translated answer with the context similar to (Hsu et al., 2019).”
- A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios (2020, background): “…and afterwards, applied to the unseen target languages, such as for named entity recognition (Lin et al., 2019; Hvingelby et al., 2020), reading comprehension (Hsu et al., 2019), temporal expression extraction (Lange et al., 2020c), or POS tagging and dependency parsing (Müller et al., 2020).”
- MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answering (2020, background): “Transfer learning techniques are often applied to these cross-lingual representations to overcome the dearth of non-English data (Cui et al., 2019a; Hsu et al., 2019; Lee and Lee, 2019; Kumar et al., 2019).”