Abstract
Recent neural headline generation models have shown great results, but are generally trained on very large datasets. We focus our efforts on improving headline quality on smaller datasets by the means of pretraining. We propose new methods that enable pre-training all the parameters of the model and utilize all available text, resulting in improvements by up to 32.4% relative in perplexity and 2.84 points in ROUGE.- Anthology ID:
- W17-4503
- Volume:
- Proceedings of the Workshop on New Frontiers in Summarization
- Month:
- September
- Year:
- 2017
- Address:
- Copenhagen, Denmark
- Venue:
- WS
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 20–26
- Language:
- URL:
- https://aclanthology.org/W17-4503
- DOI:
- 10.18653/v1/W17-4503
- Cite (ACL):
- Ottokar Tilk and Tanel Alumäe. 2017. Low-Resource Neural Headline Generation. In Proceedings of the Workshop on New Frontiers in Summarization, pages 20–26, Copenhagen, Denmark. Association for Computational Linguistics.
- Cite (Informal):
- Low-Resource Neural Headline Generation (Tilk & Alumäe, 2017)
- PDF:
- https://preview.aclanthology.org/starsem-semeval-split/W17-4503.pdf