Abstract
Expository documents are vital resources for conveying complex information to readers. Despite their usefulness, writing expository text by hand is a challenging process that requires careful content planning, obtaining facts from multiple sources, and the ability to clearly synthesize these facts. To ease these burdens, we propose the task of expository text generation, which seeks to automatically generate an accurate and stylistically consistent expository text for a topic by intelligently searching a knowledge source. We solve our task by developing IRP, a framework that overcomes the limitations of retrieval-augmented models and iteratively performs content planning, fact retrieval, and rephrasing. Through experiments on three diverse, newly-collected datasets, we show that IRP produces factual and organized expository texts that accurately inform readers.- Anthology ID:
- 2023.emnlp-main.729
- Volume:
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 11896–11919
- Language:
- URL:
- https://aclanthology.org/2023.emnlp-main.729
- DOI:
- 10.18653/v1/2023.emnlp-main.729
- Cite (ACL):
- Nishant Balepur, Jie Huang, and Kevin Chang. 2023. Expository Text Generation: Imitate, Retrieve, Paraphrase. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 11896–11919, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Expository Text Generation: Imitate, Retrieve, Paraphrase (Balepur et al., EMNLP 2023)
- PDF:
- https://preview.aclanthology.org/improve-issue-templates/2023.emnlp-main.729.pdf