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 help 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 incorpo- rated with subtopic planning can produce high- quality, diverse narratives evaluated using auto- matic metrics and human assessment.

Venue / Year

Proceedings of the EMNLP Workshop on Generation, Evaluation & Metrics (GEM) / 2022

Links

Anthology | Paper | Presentation | BibTeX