Abstract
We present a method for generating comparative summaries that highlight similarities and contradictions in input documents. The key challenge in creating such summaries is the lack of large parallel training data required for training typical summarization systems. To this end, we introduce a hybrid generation approach inspired by traditional concept-to-text systems. To enable accurate comparison between different sources, the model first learns to extract pertinent relations from input documents. The content planning component uses deterministic operators to aggregate these relations after identifying a subset for inclusion into a summary. The surface realization component lexicalizes this information using a text-infilling language model. By separately modeling content selection and realization, we can effectively train them with limited annotations. We implemented and tested the model in the domain of nutrition and health – rife with inconsistencies. Compared to conventional methods, our framework leads to more faithful, relevant and aggregation-sensitive summarization – while being equally fluent.- Anthology ID:
- 2021.naacl-main.411
- Volume:
- Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
- Month:
- June
- Year:
- 2021
- Address:
- Online
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 5213–5222
- Language:
- URL:
- https://aclanthology.org/2021.naacl-main.411
- DOI:
- 10.18653/v1/2021.naacl-main.411
- Cite (ACL):
- Darsh Shah, Lili Yu, Tao Lei, and Regina Barzilay. 2021. Nutri-bullets Hybrid: Consensual Multi-document Summarization. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5213–5222, Online. Association for Computational Linguistics.
- Cite (Informal):
- Nutri-bullets Hybrid: Consensual Multi-document Summarization (Shah et al., NAACL 2021)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2021.naacl-main.411.pdf
- Data
- Healthline