Abstract
Many modern neural document summarization systems based on encoder-decoder networks are designed to produce abstractive summaries. We attempted to verify the degree of abstractiveness of modern neural abstractive summarization systems by calculating overlaps in terms of various types of units. Upon the observation that many abstractive systems tend to be near-extractive in practice, we also implemented a pure copy system, which achieved comparable results as abstractive summarizers while being far more computationally efficient. These findings suggest the possibility for future efforts towards more efficient systems that could better utilize the vocabulary in the original document.- Anthology ID:
- D18-1089
- Volume:
- Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
- Month:
- October-November
- Year:
- 2018
- Address:
- Brussels, Belgium
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 785–790
- Language:
- URL:
- https://aclanthology.org/D18-1089
- DOI:
- 10.18653/v1/D18-1089
- Cite (ACL):
- Fangfang Zhang, Jin-ge Yao, and Rui Yan. 2018. On the Abstractiveness of Neural Document Summarization. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 785–790, Brussels, Belgium. Association for Computational Linguistics.
- Cite (Informal):
- On the Abstractiveness of Neural Document Summarization (Zhang et al., EMNLP 2018)
- PDF:
- https://preview.aclanthology.org/nodalida-main-page/D18-1089.pdf
- Data
- CNN/Daily Mail