Temporal Question Generation from History Text

Harsimran Bedi, Sangameshwar Patil, Girish Palshikar


Abstract
Temporal analysis of history text has always held special significance to students, historians and the Social Sciences community in general. We observe from experimental data that existing deep learning (DL) models of ProphetNet and UniLM for question generation (QG) task do not perform satisfactorily when used directly for temporal QG from history text. We propose linguistically motivated templates for generating temporal questions that probe different aspects of history text and show that finetuning the DL models using the temporal questions significantly improves their performance on temporal QG task. Using automated metrics as well as human expert evaluation, we show that performance of the DL models finetuned with the template-based questions is better than finetuning done with temporal questions from SQuAD.
Anthology ID:
2021.icon-main.49
Volume:
Proceedings of the 18th International Conference on Natural Language Processing (ICON)
Month:
December
Year:
2021
Address:
National Institute of Technology Silchar, Silchar, India
Venue:
ICON
SIG:
Publisher:
NLP Association of India (NLPAI)
Note:
Pages:
408–413
Language:
URL:
https://aclanthology.org/2021.icon-main.49
DOI:
Bibkey:
Cite (ACL):
Harsimran Bedi, Sangameshwar Patil, and Girish Palshikar. 2021. Temporal Question Generation from History Text. In Proceedings of the 18th International Conference on Natural Language Processing (ICON), pages 408–413, National Institute of Technology Silchar, Silchar, India. NLP Association of India (NLPAI).
Cite (Informal):
Temporal Question Generation from History Text (Bedi et al., ICON 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2021.icon-main.49.pdf
Optional supplementary material:
 2021.icon-main.49.OptionalSupplementaryMaterial.zip