Abstract
Emerged as one of the best performing techniques for extractive summarization, determinantal point processes select a most probable set of summary sentences according to a probabilistic measure defined by respectively modeling sentence prominence and pairwise repulsion. Traditionally, both aspects are modelled using shallow and linguistically informed features, but the rise of deep contextualized representations raises an interesting question. Whether, and to what extent, could contextualized sentence representations be used to improve the DPP framework? Our findings suggest that, despite the success of deep semantic representations, it remains necessary to combine them with surface indicators for effective identification of summary-worthy sentences.- Anthology ID:
- D19-5412
- Volume:
- Proceedings of the 2nd Workshop on New Frontiers in Summarization
- Month:
- November
- Year:
- 2019
- Address:
- Hong Kong, China
- Venue:
- WS
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 98–103
- Language:
- URL:
- https://aclanthology.org/D19-5412
- DOI:
- 10.18653/v1/D19-5412
- Cite (ACL):
- Sangwoo Cho, Chen Li, Dong Yu, Hassan Foroosh, and Fei Liu. 2019. Multi-Document Summarization with Determinantal Point Processes and Contextualized Representations. In Proceedings of the 2nd Workshop on New Frontiers in Summarization, pages 98–103, Hong Kong, China. Association for Computational Linguistics.
- Cite (Informal):
- Multi-Document Summarization with Determinantal Point Processes and Contextualized Representations (Cho et al., 2019)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/D19-5412.pdf