Natural Answer Generation: From Factoid Answer to Full-length Answer using Grammar Correction

Manas Jain, Sriparna Saha, Pushpak Bhattacharyya, Gladvin Chinnadurai, Manish Vatsa


Abstract
Question Answering systems these days typically use template-based language generation. Though adequate for a domain-specific task, these systems are too restrictive and predefined for domain-independent systems. This paper proposes a system that outputs a full-length answer given a question and the extracted factoid answer (short spans such as named entities) as the input. Our system uses constituency and dependency parse trees of questions. A transformer-based Grammar Error Correction model GECToR is used as a post-processing step for better fluency. We compare our system with (i) a Modified Pointer Generator (SOTA) and (ii) Fine-tuned DialoGPT for factoid questions. We also tested our approach on existential (yes-no) questions with better results. Our model generates more accurate and fluent answers than the state-of-the-art (SOTA) approaches. The evaluation is done on NewsQA and SqUAD datasets with an increment of 0.4 and 0.9 percentage points in ROUGE-1 score respectively. Also, the inference time is reduced by 85% compared to the SOTA. The improved datasets used for our evaluation will be released as part of the research contribution.
Anthology ID:
2024.icon-1.43
Volume:
Proceedings of the 21st International Conference on Natural Language Processing (ICON)
Month:
December
Year:
2024
Address:
AU-KBC Research Centre, Chennai, India
Editors:
Sobha Lalitha Devi, Karunesh Arora
Venue:
ICON
SIG:
Publisher:
NLP Association of India (NLPAI)
Note:
Pages:
376–385
Language:
URL:
https://aclanthology.org/2024.icon-1.43/
DOI:
Bibkey:
Cite (ACL):
Manas Jain, Sriparna Saha, Pushpak Bhattacharyya, Gladvin Chinnadurai, and Manish Vatsa. 2024. Natural Answer Generation: From Factoid Answer to Full-length Answer using Grammar Correction. In Proceedings of the 21st International Conference on Natural Language Processing (ICON), pages 376–385, AU-KBC Research Centre, Chennai, India. NLP Association of India (NLPAI).
Cite (Informal):
Natural Answer Generation: From Factoid Answer to Full-length Answer using Grammar Correction (Jain et al., ICON 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.icon-1.43.pdf