Generating Coherent Narratives with Subtopic Planning to Answer How-to Questions

Pengshan Cai, Mo Yu, Fei Liu, Hong Yu


Abstract
Answering how-to questions remains a major challenge in question answering research. A vast number of narrow, long-tail questions cannot be readily answered using a search engine. Moreover, there is little to no annotated data available to develop such systems. This paper makes a first attempt at generating coherent, long-form answers for how-to questions. We propose new architectures, consisting of passage retrieval, subtopic planning and narrative generation, to consolidate multiple relevant passages into a coherent, explanatory answer. Our subtopic planning module aims to produce a set of relevant, diverse subtopics that serve as the backbone for answer generation to improve topic coherence. We present extensive experiments on a WikiHow dataset repurposed for long-form question answering. Empirical results demonstrate that generating narratives to answer how-to questions is a challenging task. Nevertheless, our architecture incorporated with subtopic planning can produce high-quality, diverse narratives evaluated using automatic metrics and human assessment.
Anthology ID:
2022.gem-1.3
Volume:
Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates (Hybrid)
Editors:
Antoine Bosselut, Khyathi Chandu, Kaustubh Dhole, Varun Gangal, Sebastian Gehrmann, Yacine Jernite, Jekaterina Novikova, Laura Perez-Beltrachini
Venue:
GEM
SIG:
SIGGEN
Publisher:
Association for Computational Linguistics
Note:
Pages:
26–42
Language:
URL:
https://aclanthology.org/2022.gem-1.3
DOI:
10.18653/v1/2022.gem-1.3
Bibkey:
Cite (ACL):
Pengshan Cai, Mo Yu, Fei Liu, and Hong Yu. 2022. Generating Coherent Narratives with Subtopic Planning to Answer How-to Questions. In Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM), pages 26–42, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.
Cite (Informal):
Generating Coherent Narratives with Subtopic Planning to Answer How-to Questions (Cai et al., GEM 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.gem-1.3.pdf
Video:
 https://aclanthology.org/2022.gem-1.3.mp4