Beyond English-Only Reading Comprehension: Experiments in Zero-shot Multilingual Transfer for Bulgarian

Momchil Hardalov, Ivan Koychev, Preslav Nakov


Abstract
Recently, reading comprehension models achieved near-human performance on large-scale datasets such as SQuAD, CoQA, MS Macro, RACE, etc. This is largely due to the release of pre-trained contextualized representations such as BERT and ELMo, which can be fine-tuned for the target task. Despite those advances and the creation of more challenging datasets, most of the work is still done for English. Here, we study the effectiveness of multilingual BERT fine-tuned on large-scale English datasets for reading comprehension (e.g., for RACE), and we apply it to Bulgarian multiple-choice reading comprehension. We propose a new dataset containing 2,221 questions from matriculation exams for twelfth grade in various subjects —history, biology, geography and philosophy—, and 412 additional questions from online quizzes in history. While the quiz authors gave no relevant context, we incorporate knowledge from Wikipedia, retrieving documents matching the combination of question + each answer option. Moreover, we experiment with different indexing and pre-training strategies. The evaluation results show accuracy of 42.23%, which is well above the baseline of 24.89%.
Anthology ID:
R19-1053
Volume:
Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)
Month:
September
Year:
2019
Address:
Varna, Bulgaria
Editors:
Ruslan Mitkov, Galia Angelova
Venue:
RANLP
SIG:
Publisher:
INCOMA Ltd.
Note:
Pages:
447–459
Language:
URL:
https://aclanthology.org/R19-1053
DOI:
10.26615/978-954-452-056-4_053
Bibkey:
Cite (ACL):
Momchil Hardalov, Ivan Koychev, and Preslav Nakov. 2019. Beyond English-Only Reading Comprehension: Experiments in Zero-shot Multilingual Transfer for Bulgarian. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019), pages 447–459, Varna, Bulgaria. INCOMA Ltd..
Cite (Informal):
Beyond English-Only Reading Comprehension: Experiments in Zero-shot Multilingual Transfer for Bulgarian (Hardalov et al., RANLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/R19-1053.pdf
Code
 mhardalov/bg-reason-BERT
Data
Bulgarian Reading Comprehension DatasetRACE